{"topic":"ai-agents","sort":"top","limit":25,"offset":0,"count":25,"papers":[{"id":"doi:10.1038/s42256-024-00832-8","kind":"article","title":"Augmenting large language models with chemistry tools","authors":["Andres M Bran","Sam Cox","Oliver Tobias Schilter","Carlo Baldassari","Andrew Dickson White","Philippe Schwaller"],"author_count":6,"year":2024,"published":"2024-05-08","venue":"Nature Machine Intelligence","cited_by":792,"doi":"10.1038/s42256-024-00832-8","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1038/s42256-024-00832-8","archive_url":"https://space-kitty.com/papers/doi:10.1038/s42256-024-00832-8","updated":null,"pmid":"38799228","pmcid":null,"openalex_id":"W4396723768","pdf_url":"https://www.nature.com/articles/s42256-024-00832-8.pdf","abstract":"Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery and materials design. By integrating 18 expert-designed tools and using GPT-4 as the LLM, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent and three organocatalysts and guided the discovery of a novel chromophore. Our evaluation, including both LLM and expert assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks. Our work not only aids expert chemists and lowers barriers for non-experts but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Machine Learning in Materials Science"],"details":null,"provenance":"openalex","attribution":"Abstract of \"Augmenting large language models with chemistry tools\" by Andres M Bran, Sam Cox, Oliver Tobias Schilter et al., https://doi.org/10.1038/s42256-024-00832-8, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"arxiv:2404.02831","kind":"review","title":"Empowering biomedical discovery with AI agents","authors":["Shanghua Gao","Ada Fang","Yepeng Huang","Valentina Giunchiglia","Ayush Noori","Jonathan Richard Schwarz","Yasha Ektefaie","Jovana Kondic","Marinka Žitnik"],"author_count":9,"year":2024,"published":"2024-10-01","venue":"Cell","cited_by":315,"doi":"10.1016/j.cell.2024.09.022","arxiv_id":"2404.02831","nct_id":null,"source_url":"https://doi.org/10.1016/j.cell.2024.09.022","archive_url":"https://space-kitty.com/papers/arxiv:2404.02831","updated":"2024-07-24","pmid":"39486399","pmcid":null,"openalex_id":"W4403925918","pdf_url":"https://arxiv.org/pdf/2404.02831","abstract":"We envision \"AI scientists\" as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate AI models and biomedical tools with experimental platforms. Rather than taking humans out of the discovery process, biomedical AI agents combine human creativity and expertise with AI's ability to analyze large datasets, navigate hypothesis spaces, and execute repetitive tasks. AI agents are poised to be proficient in various tasks, planning discovery workflows and performing self-assessment to identify and mitigate gaps in their knowledge. These agents use large language models and generative models to feature structured memory for continual learning and use machine learning tools to incorporate scientific knowledge, biological principles, and theories. AI agents can impact areas ranging from virtual cell simulation, programmable control of phenotypes, and the design of cellular circuits to developing new therapies.","abstract_license":"CC0-1.0 (arXiv descriptive metadata)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex+arxiv","attribution":"Abstract: arXiv descriptive metadata (CC0). Thank you to arXiv for use of its open access interoperability. This service was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv."},{"id":"openalex:W3037786853","kind":"article","title":"2004, “From System Dynamics and Discrete Event to Practical Agent Based Modeling: Reasons, Techniques, Tools","authors":["Andrei V. Borshchev"],"author_count":1,"year":2011,"published":"2011-10-29","venue":null,"cited_by":501,"doi":null,"arxiv_id":null,"nct_id":null,"source_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.200.9920","archive_url":"https://space-kitty.com/papers/openalex:W3037786853","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W3037786853","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Simulation Techniques and Applications"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"arxiv:2404.18021","kind":"article","title":"CRISPR-GPT for agentic automation of gene-editing experiments","authors":["Yuanhao Qu","Kaixuan Huang","Ming Yin","Kanghong Zhan","Dyllan Liu","Di Yin","Henry C. Cousins","William A. Johnson","Xiaotong Wang","Mihir M. Shah","Russ Biagio Altman","Denny Zhou","Mengdi Wang","Le Cong"],"author_count":14,"year":2025,"published":"2025-07-30","venue":"Nature Biomedical Engineering","cited_by":146,"doi":"10.1038/s41551-025-01463-z","arxiv_id":"2404.18021","nct_id":null,"source_url":"https://doi.org/10.1038/s41551-025-01463-z","archive_url":"https://space-kitty.com/papers/arxiv:2404.18021","updated":"2025-08-21","pmid":"39463961","pmcid":null,"openalex_id":"W4412759774","pdf_url":"https://arxiv.org/pdf/2404.18021","abstract":"The introduction of genome engineering technology has transformed biomedical research, making it possible to make precise changes to genetic information. However, creating an efficient gene-editing system requires a deep understanding of CRISPR technology, and the complex experimental systems under investigation. While Large Language Models (LLMs) have shown promise in various tasks, they often lack specific knowledge and struggle to accurately solve biological design problems. In this work, we introduce CRISPR-GPT, an LLM agent augmented with domain knowledge and external tools to automate and enhance the design process of CRISPR-based gene-editing experiments. CRISPR-GPT leverages the reasoning ability of LLMs to facilitate the process of selecting CRISPR systems, designing guide RNAs, recommending cellular delivery methods, drafting protocols, and designing validation experiments to confirm editing outcomes. We showcase the potential of CRISPR-GPT for assisting non-expert researchers with gene-editing experiments from scratch and validate the agent's effectiveness in a real-world use case. Furthermore, we explore the ethical and regulatory considerations associated with automated gene-editing design, highlighting the need for responsible and transparent use of these tools. Our work aims to bridge the gap between beginner biological researchers and CRISPR genome engineering techniques, and demonstrate the potential of LLM agents in facilitating complex biological discovery tasks. The published version of this draft is available at https://www.nature.com/articles/s41551-025-01463-z.","abstract_license":"CC0-1.0 (arXiv descriptive metadata)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["CRISPR and Genetic Engineering"],"details":null,"provenance":"openalex+arxiv","attribution":"Abstract: arXiv descriptive metadata (CC0). Thank you to arXiv for use of its open access interoperability. This service was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv."},{"id":"doi:10.1038/s41578-025-00772-8","kind":"review","title":"Large language models for reticular chemistry","authors":["Zhiling Zheng","Nakul Rampal","Théo Jaffrelot Inizan","Christian Borgs","Jennifer Chayes","Omar M. Yaghi"],"author_count":6,"year":2025,"published":"2025-01-31","venue":"Nature Reviews Materials","cited_by":134,"doi":"10.1038/s41578-025-00772-8","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1038/s41578-025-00772-8","archive_url":"https://space-kitty.com/papers/doi:10.1038/s41578-025-00772-8","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4407024439","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Machine Learning in Materials Science"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"doi:10.1101/2025.05.30.656746","kind":"article","title":"Biomni: A General-Purpose Biomedical AI Agent","authors":["Kexin Huang","Serena Zhang","Hanchen Wang","Yuanhao Qu","Yingzhou Lu","Yusuf Roohani","Ryan J. Li","Lin Qiu","G. L. Li","Junze Zhang","Di Yin","Shruti Marwaha","Jennefer N. Carter","Xin Zhou","Matthew Thomas Wheeler","Jonathan Adam Bernstein","Mengdi Wang","Peng He","Jingtian Zhou","Michael P. Snyder","Le Cong","Aviv Regev","Jure Leskovec"],"author_count":23,"year":2025,"published":"2025-06-02","venue":"bioRxiv (Cold Spring Harbor Laboratory)","cited_by":124,"doi":"10.1101/2025.05.30.656746","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1101/2025.05.30.656746","archive_url":"https://space-kitty.com/papers/doi:10.1101/2025.05.30.656746","updated":null,"pmid":"40501924","pmcid":null,"openalex_id":"W4411005431","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/06/02/2025.05.30.656746.full.pdf","abstract":"Biomedical research underpins progress in our understanding of human health and disease, drug discovery, and clinical care. However, with the growth of complex lab experiments, large datasets, many analytical tools, and expansive literature, biomedical research is increasingly constrained by repetitive and fragmented workflows that slow discovery and limit innovation, underscoring the need for a fundamentally new way to scale scientific expertise. Here, we introduce Biomni, a general-purpose biomedical AI agent designed to autonomously execute a wide spectrum of research tasks across diverse biomedical subfields. To systematically map the biomedical action space, Biomni first employs an action discovery agent to create the first unified agentic environment - mining essential tools, databases, and protocols from tens of thousands of publications across 25 biomedical domains. Built on this foundation, Biomni features a generalist agentic architecture that integrates large language model (LLM) reasoning with retrieval-augmented planning and code-based execution, enabling it to dynamically compose and carry out complex biomedical workflows - entirely without relying on predefined templates or rigid task flows. Systematic benchmarking demonstrates that Biomni achieves strong generalization across heterogeneous biomedical tasks - including causal gene prioritization, drug repurposing, rare disease diagnosis, microbiome analysis, and molecular cloning - without any task-specific prompt tuning. Real-world case studies further showcase Biomni's ability to interpret complex, multi-modal biomedical datasets and autonomously generate experimentally testable protocols. Biomni envisions a future where virtual AI biologists operate alongside and augment human scientists to dramatically enhance research productivity, clinical insight, and healthcare. Biomni is ready to use at https://biomni.stanford.edu, and we invite scientists to explore its capabilities, stress-test its limits, and co-create the next era of biomedical discoveries.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Biomedical Text Mining and Ontologies"],"details":null,"provenance":"openalex","attribution":"Abstract of \"Biomni: A General-Purpose Biomedical AI Agent\" by Kexin Huang, Serena Zhang, Hanchen Wang et al., https://doi.org/10.1101/2025.05.30.656746, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"doi:10.2337/dc23-0197","kind":"article","title":"Potential and Pitfalls of ChatGPT and Natural-Language Artificial Intelligence Models for Diabetes Education","authors":["Gerald Gui Ren Sng","Joshua Yi Min Tung","Daniel Yan Zheng Lim","Yong Mong Bee"],"author_count":4,"year":2023,"published":"2023-03-15","venue":"Diabetes Care","cited_by":160,"doi":"10.2337/dc23-0197","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.2337/dc23-0197","archive_url":"https://space-kitty.com/papers/doi:10.2337/dc23-0197","updated":null,"pmid":"36920843","pmcid":null,"openalex_id":"W4324311092","pdf_url":"https://diabetesjournals.org/care/article-pdf/doi/10.2337/dc23-0197/700123/dc230197.pdf","abstract":null,"abstract_license":null,"license":null,"is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"doi:10.1145/3715754","kind":"article","title":"Demystifying LLM-Based Software Engineering Agents","authors":["Chunqiu Steven Xia","Yinlin Deng","Soren Dunn","Lingming Zhang"],"author_count":4,"year":2025,"published":"2025-06-19","venue":"Proceedings of the ACM on software engineering.","cited_by":115,"doi":"10.1145/3715754","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1145/3715754","archive_url":"https://space-kitty.com/papers/doi:10.1145/3715754","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4411449940","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3715754","abstract":"Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry practitioners have developed various autonomous LLM agents to perform end-to-end software development tasks. These agents are equipped with the ability to use tools, run commands, observe feedback from the environment, and plan for future actions. However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents? To attempt to answer this question, we build Agentless – an agentless approach to automatically resolve software development issues. Compared to the verbose and complex setup of agent-based approaches, Agentless employs a simplistic three-phase process of localization, repair, and patch validation, without letting the LLM decide future actions or operate with complex tools. Our results on the popular SWE-bench Lite benchmark show that surprisingly the simplistic Agentless is able to achieve both the highest performance (32.00%, 96 correct fixes) and low cost ($0.70) compared with all existing open-source software agents at the time of paper submission! Agentless also achieves more than 50% solve rate when using Claude 3.5 Sonnet on the new SWE-bench Verified benchmark. In fact, Agentless has already been adopted by OpenAI as the go-to approach to showcase the real-world coding performance of both GPT-4o and the new o1 models; more recently, Agentless has also been used by DeepSeek to evaluate their newest DeepSeek V3 and R1 models . Furthermore, we manually classified the problems in SWE-bench Lite and found problems with exact ground truth patches or insufficient/misleading issue descriptions. As such, we construct SWE-bench Lite- S by excluding such problematic issues to perform more rigorous evaluation and comparison. Our work highlights the currently overlooked potential of a simplistic, cost-effective technique in autonomous software development. We hope Agentless will help reset the baseline, starting point, and horizon for autonomous software agents, and inspire future work along this crucial direction. We have open-sourced Agentless at: https://github.com/OpenAutoCoder/Agentless","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Software Engineering Research"],"details":null,"provenance":"openalex","attribution":"Abstract of \"Demystifying LLM-Based Software Engineering Agents\" by Chunqiu Steven Xia, Yinlin Deng, Soren Dunn et al., https://doi.org/10.1145/3715754, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"doi:10.1177/0037549712462620","kind":"article","title":"Parallel agent-based simulation with Repast for High Performance Computing","authors":["Nicholson T. Collier","MICHAEL J. NORTH"],"author_count":2,"year":2012,"published":"2012-11-06","venue":"SIMULATION","cited_by":215,"doi":"10.1177/0037549712462620","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1177/0037549712462620","archive_url":"https://space-kitty.com/papers/doi:10.1177/0037549712462620","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W2103821666","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Simulation Techniques and Applications"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"arxiv:2312.07850","kind":"article","title":"Large Language Model Enhanced Multi-Agent Systems for 6G Communications","authors":["Feibo Jiang","Yubo Peng","Li Dong","Kezhi Wang","Kun Yang","Cunhua Pan","Dusit Tao Niyato","Octavia A. Dobre"],"author_count":8,"year":2024,"published":"2024-08-16","venue":"IEEE Wireless Communications","cited_by":123,"doi":"10.1109/mwc.016.2300600","arxiv_id":"2312.07850","nct_id":null,"source_url":"https://doi.org/10.1109/mwc.016.2300600","archive_url":"https://space-kitty.com/papers/arxiv:2312.07850","updated":"2023-12-13","pmid":null,"pmcid":null,"openalex_id":"W4401628481","pdf_url":"https://arxiv.org/pdf/2312.07850","abstract":"The rapid development of the Large Language Model (LLM) presents huge opportunities for 6G communications, e.g., network optimization and management by allowing users to input task requirements to LLMs by nature language. However, directly applying native LLMs in 6G encounters various challenges, such as a lack of private communication data and knowledge, limited logical reasoning, evaluation, and refinement abilities. Integrating LLMs with the capabilities of retrieval, planning, memory, evaluation and reflection in agents can greatly enhance the potential of LLMs for 6G communications. To this end, we propose a multi-agent system with customized communication knowledge and tools for solving communication related tasks using natural language, comprising three components: (1) Multi-agent Data Retrieval (MDR), which employs the condensate and inference agents to refine and summarize communication knowledge from the knowledge base, expanding the knowledge boundaries of LLMs in 6G communications; (2) Multi-agent Collaborative Planning (MCP), which utilizes multiple planning agents to generate feasible solutions for the communication related task from different perspectives based on the retrieved knowledge; (3) Multi-agent Evaluation and Reflecxion (MER), which utilizes the evaluation agent to assess the solutions, and applies the reflexion agent and refinement agent to provide improvement suggestions for current solutions. Finally, we validate the effectiveness of the proposed multi-agent system by designing a semantic communication system, as a case study of 6G communications.","abstract_license":"CC0-1.0 (arXiv descriptive metadata)","license":null,"is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Multi-Agent Systems and Negotiation"],"details":null,"provenance":"openalex+arxiv","attribution":"Abstract: arXiv descriptive metadata (CC0). Thank you to arXiv for use of its open access interoperability. This service was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv."},{"id":"arxiv:1909.07528","kind":"preprint","title":"Emergent Tool Use From Multi-Agent Autocurricula","authors":["Bowen Baker","Ingmar Kanitscheider","Todor Markov","Yi Wu","Glenn Powell","Bob McGrew","Igor Mordatch"],"author_count":7,"year":2019,"published":"2019-09-17","venue":null,"cited_by":424,"doi":null,"arxiv_id":"1909.07528","nct_id":null,"source_url":"https://arxiv.org/abs/1909.07528","archive_url":"https://space-kitty.com/papers/arxiv:1909.07528","updated":"2020-02-11","pmid":null,"pmcid":null,"openalex_id":"W2973525135","pdf_url":"https://arxiv.org/pdf/1909.07528","abstract":"Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent strategy, many of which require sophisticated tool use and coordination. We find clear evidence of six emergent phases in agent strategy in our environment, each of which creates a new pressure for the opposing team to adapt; for instance, agents learn to build multi-object shelters using moveable boxes which in turn leads to agents discovering that they can overcome obstacles using ramps. We further provide evidence that multi-agent competition may scale better with increasing environment complexity and leads to behavior that centers around far more human-relevant skills than other self-supervised reinforcement learning methods such as intrinsic motivation. Finally, we propose transfer and fine-tuning as a way to quantitatively evaluate targeted capabilities, and we compare hide-and-seek agents to both intrinsic motivation and random initialization baselines in a suite of domain-specific intelligence tests.","abstract_license":"CC0-1.0 (arXiv descriptive metadata)","license":null,"is_open_access":false,"retracted":false,"peer_reviewed":false,"categories":["cs.LG","cs.AI","cs.MA","stat.ML"],"details":null,"provenance":"arxiv","attribution":"Abstract: arXiv descriptive metadata (CC0). Thank you to arXiv for use of its open access interoperability. This service was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv."},{"id":"doi:10.1038/s41586-025-08661-4","kind":"article","title":"Optimizing generative AI by backpropagating language model feedback","authors":["Mert Yüksekgönül","Federico Bianchi","Joseph Boen","Sheng Liu","Pan Lu","Zhi Huang","Carlos Guestrin","James Zou"],"author_count":8,"year":2025,"published":"2025-03-19","venue":"Nature","cited_by":85,"doi":"10.1038/s41586-025-08661-4","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1038/s41586-025-08661-4","archive_url":"https://space-kitty.com/papers/doi:10.1038/s41586-025-08661-4","updated":null,"pmid":"40108317","pmcid":null,"openalex_id":"W4408612787","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence Applications"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"doi:10.5286/dltr.2010007","kind":"article","title":"Survey of Agent Based Modelling and Simulation Tools","authors":["RJ Allan"],"author_count":1,"year":2010,"published":"2010-01-01","venue":"Science and Technology Facilities Council","cited_by":159,"doi":"10.5286/dltr.2010007","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.5286/dltr.2010007","archive_url":"https://space-kitty.com/papers/doi:10.5286/dltr.2010007","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W2241934096","pdf_url":null,"abstract":"Agent Based Modelling and Simulation is a computationally demanding technique having itsorigins in discrete event simulation, genetic algorithms and cellular automata. It is a powerful technique for simulating dynamic complex systems and observing \"emergent\" behaviour. There is currently a lot of interest in developing ABMs as a general computational technique applicable to the study of large scale systems. ABMs has been adapted to run on novel architectures such as GPGPU, e.g. nVidia hardware using the CUDA programming language. Argonne National Laboratory have a Web site on Exascale ABMs and have run models on the IBM BlueGene with funding from the SciDAC Programme. The most common uses of ABMs are in social simulation and optimisation problems, such as crowd behaviour, urban simulation, traffic flow and supply chains. We will investigate other uses in computational science, particularly in engineering and systems biology.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Simulation Techniques and Applications"],"details":null,"provenance":"openalex","attribution":"Abstract of \"Survey of Agent Based Modelling and Simulation Tools\" by RJ Allan, https://doi.org/10.5286/dltr.2010007, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"doi:10.1007/s10514-023-10136-2","kind":"article","title":"Large language models for chemistry robotics","authors":["Naruki Yoshikawa","Marta Skreta","Kourosh Darvish","Sebastian Arellano-Rubach","Zhi Ji","Lasse Bjørn Kristensen","Andrew Zou Li","Yuchi Zhao","Haoping Xu","Artur Kuramshin","Alán Aspuru‐Guzik","Florian Shkurti","Animesh Garg"],"author_count":13,"year":2023,"published":"2023-10-25","venue":"Autonomous Robots","cited_by":112,"doi":"10.1007/s10514-023-10136-2","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1007/s10514-023-10136-2","archive_url":"https://space-kitty.com/papers/doi:10.1007/s10514-023-10136-2","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4387937021","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10514-023-10136-2.pdf","abstract":"Abstract This paper proposes an approach to automate chemistry experiments using robots by translating natural language instructions into robot-executable plans, using large language models together with task and motion planning. Adding natural language interfaces to autonomous chemistry experiment systems lowers the barrier to using complicated robotics systems and increases utility for non-expert users, but translating natural language experiment descriptions from users into low-level robotics languages is nontrivial. Furthermore, while recent advances have used large language models to generate task plans, reliably executing those plans in the real world by an embodied agent remains challenging. To enable autonomous chemistry experiments and alleviate the workload of chemists, robots must interpret natural language commands, perceive the workspace, autonomously plan multi-step actions and motions, consider safety precautions, and interact with various laboratory equipment. Our approach, CLAIRify , combines automatic iterative prompting with program verification to ensure syntactically valid programs in a data-scarce domain-specific language that incorporates environmental constraints. The generated plan is executed through solving a constrained task and motion planning problem using PDDLStream solvers to prevent spillages of liquids as well as collisions in chemistry labs. We demonstrate the effectiveness of our approach in planning chemistry experiments, with plans successfully executed on a real robot using a repertoire of robot skills and lab tools. Specifically, we showcase the utility of our framework in pouring skills for various materials and two fundamental chemical experiments for materials synthesis: solubility and recrystallization. Further details about CLAIRify can be found at https://ac-rad.github.io/clairify/ .","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["AI-based Problem Solving and Planning"],"details":null,"provenance":"openalex","attribution":"Abstract of \"Large language models for chemistry robotics\" by Naruki Yoshikawa, Marta Skreta, Kourosh Darvish et al., https://doi.org/10.1007/s10514-023-10136-2, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"doi:10.1016/j.imed.2025.03.002","kind":"article","title":"Evaluating large language models and agents in healthcare: key challenges in clinical applications","authors":["Xiaolan Chen","Jiayang Xiang","Shanfu Lu","Yexin Liu","Mingguang He","Danli Shi"],"author_count":6,"year":2025,"published":"2025-04-02","venue":"Intelligent Medicine","cited_by":75,"doi":"10.1016/j.imed.2025.03.002","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.imed.2025.03.002","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.imed.2025.03.002","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4409091111","pdf_url":null,"abstract":null,"abstract_license":null,"license":"cc-by-nc-nd","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"arxiv:2503.23037","kind":"article","title":"Agentic Large Language Models, a Survey","authors":["Aske Plaat","Max J. van Duijn","Bas van Stein","Mike Preuß","Peter van der Putten","Kees Joost Batenburg"],"author_count":6,"year":2025,"published":"2025-12-30","venue":"Journal of Artificial Intelligence Research","cited_by":74,"doi":"10.1613/jair.1.18675","arxiv_id":"2503.23037","nct_id":null,"source_url":"https://doi.org/10.1613/jair.1.18675","archive_url":"https://space-kitty.com/papers/arxiv:2503.23037","updated":"2025-11-22","pmid":null,"pmcid":null,"openalex_id":"W4409318329","pdf_url":"https://arxiv.org/pdf/2503.23037","abstract":"Background: There is great interest in agentic LLMs, large language models that act as agents. Objectives: We review the growing body of work in this area and provide a research agenda. Methods: Agentic LLMs are LLMs that (1) reason, (2) act, and (3) interact. We organize the literature according to these three categories. Results: The research in the first category focuses on reasoning, reflection, and retrieval, aiming to improve decision making; the second category focuses on action models, robots, and tools, aiming for agents that act as useful assistants; the third category focuses on multi-agent systems, aiming for collaborative task solving and simulating interaction to study emergent social behavior. We find that works mutually benefit from results in other categories: retrieval enables tool use, reflection improves multi-agent collaboration, and reasoning benefits all categories. Conclusions: We discuss applications of agentic LLMs and provide an agenda for further research. Important applications are in medical diagnosis, logistics and financial market analysis. Meanwhile, self-reflective agents playing roles and interacting with one another augment the process of scientific research itself. Further, agentic LLMs provide a solution for the problem of LLMs running out of training data: inference-time behavior generates new training states, such that LLMs can keep learning without needing ever larger datasets. We note that there is risk associated with LLM assistants taking action in the real world-safety, liability and security are open problems-while agentic LLMs are also likely to benefit society.","abstract_license":"CC0-1.0 (arXiv descriptive metadata)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Topic Modeling"],"details":null,"provenance":"openalex+arxiv","attribution":"Abstract: arXiv descriptive metadata (CC0). Thank you to arXiv for use of its open access interoperability. This service was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv."},{"id":"doi:10.1016/j.jhep.2023.07.028","kind":"article","title":"ChatGPT: The transformative influence of generative AI on science and healthcare","authors":["Julian Varghese","Julius Chapiro"],"author_count":2,"year":2023,"published":"2023-08-06","venue":"Journal of Hepatology","cited_by":94,"doi":"10.1016/j.jhep.2023.07.028","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.jhep.2023.07.028","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.jhep.2023.07.028","updated":null,"pmid":"37544516","pmcid":null,"openalex_id":"W4385605341","pdf_url":"http://www.journal-of-hepatology.eu/article/S0168827823050390/pdf","abstract":"“To improve is to change; to be perfect is to change often.” ― Winston S. Churchill. In a time and age where technology is evolving at a sometimes incomprehensibly rapid pace, the liver community must grow with its challenges and adjust our practices to transformative influences on our science and practice. The Editorial Board of the Journal of Hepatology has previously responded to novel developments in Artificial Intelligence (AI) by including experts in the field into the editorial board. Publications utilizing AI technology are no longer uncommon in our journal and have become among the most highly debated and possibly practice-changing papers across all disciplines united by our focus on liver disease. As AI is rapidly evolving, this expert paper will focus on large language models and their possible impact on our research practice and clinical outlook, outlining both challenges and opportunities in the field. Generative AI creates new content, such as text, images, or music, based on patterns in the data it has been trained on. If Generative AI utilizes Large Language Models, it involves training on extensive text datasets and employing AI models with a large number of model parameters. ChatGPT (General Pretrained Transformers) is a popular example of a Generative AI that utilizes Large Language Models. It was developed by OpenAI, version 3.5 released in November 2022, then updated to its superior version 4.0 – called GPT-4 - in March 2023 and version 5 expected to be released in the near future. Figure 1 illustrates the terminology within the overarching concept of Artificial Intelligence (AI). The term AI was coined by McCarthy in the 1950s [1]Shannon CE, McCarthy J, Ashby WR. Automata studies. Princeton University Press. 1956;Google Scholar and describes a system that can mimic human behavior. This can be realized via expert-driven rule-based systems or by data-driven training via Machine Learning. The latter is capable of accomplishing classification tasks based on predetermined categories and features, e.g. recognizing patterns in data that have been previously labeled by an expert on a training data set. Deep Learning architectures are a specific subtype of Machine Learning that utilize an Artificial Neural Network design characterized by an input layer for data intake, multiple hidden layers of data analyses, and finally an output layer that characterizes the original data according to either a predetermined classification task or outlines freshly identified patterns in data that have not yet been identified by the human observer. While classical supervised Machine or Deep Learning requires labeled training data and provides a reduced fixed output like a numerical prediction (e.g. “this patient with Hepatocellular carcinoma will benefit from immunotherapy with 90% certainty”), unsupervised Neural Networks do not require labelled data and are able to detect previously unknown patterns in data. An advancement is semi-supervised Generative AI, which is trained on unlabeled data and then fine-tuned for specific supervised tasks. It can create more complex output based on input prompts and – in its most advanced version – may generate entirely new data contexts. For instance, ChatGPT utilizes transformer Neural Networks, which are pre-trained on unlabeled large text corpora to acquire a comprehensive understanding of language patterns. At this stage it is called a Large Langue Model. The model is then further fine-tuned in order to answer user prompts. The principal approach of pre-training and finetuning can be adapted for different tasks beyond text data. For instance, new realistic images can be generated based on user-prompts, as showcased by Dall-E, another creation of OpenAI. [2]Marcus G, Davis E, Aaronson S. A very preliminary analysis of DALL-E 2 [Internet]. arXiv; 2022 [cited 2023 Jun 24]. Available from: http://arxiv.org/abs/2204.13807Google Scholar. Based on the aforementioned recent advancement of Artificial Neural Networks, which are powered by increasing hardware resources and the immense amount of available human-written text that serves as training basis, ChatGPT generates human-like text better than most other Natural Language Processing tools [3]Deng J. Lin Y. The Benefits and Challenges of ChatGPT: An Overview.Frontiers in Computing and Intelligent Systems. 2022; 2: 81-83Crossref Google Scholar. It is highly effective in generating well-formulated text, which will be disruptive in the way we are going to create text, including academic writing in the biomedical domain. Users can type in raw text containing bullet points or subheadings, which can be processed by ChatGPT to coherent text, allowing the user to carefully refine and thereby creating well-written and meaningful text. In particular, this will be helpful for non-native speakers by enabling technology-based democratization of language skills. The advanced processing of language syntax has the ability to improve upon existing language input and semantically add to the initial prompt while generating explanations, references or – in the best case scenario – fact-check the existing reasoning as offered by the primary end user. In addition to the advantages of promising text completion or supporting writing skills, some early applications have been systematically tested for specific tasks. These include supporting computer programmers in advanced tasks such as converting or generating programming source code, proof-reading code and bug-fixing ,[4]Surameery N.M.S. Shakor M.Y. Use Chat GPT to Solve Programming Bugs.International Journal of Information Technology & Computer Engineering (IJITC). 2023 Jan 28; 3 (ISSN : 2455-5290): 17-22Crossref Google Scholar, classifying hate-speeches on twitter [5]Huang F, Kwak H, An J. Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech. In: Companion Proceedings of the ACM Web Conference 2023 [Internet]. New York, NY, USA: Association for Computing Machinery; 2023 [cited 2023 May 28]. p. 294–7. (WWW ’23 Companion). Available from: https://dl.acm.org/doi/10.1145/3543873.3587368Google Scholar or passing the USMLE medical exam [6]Kung T.H. Cheatham M. Medenilla A. Sillos C. Leon L.D. Elepaño C. et al.Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models.PLOS Digital Health. 2023 Feb 9; 2e0000198Crossref Google Scholar. The performances range from moderate to high, which is impressive considering that ChatGPT was never fine-tuned for these specialized applications, is limited to data input before the year 2022 and shows its applicability as an easy-to use general purpose AI. It remains to be seen if future variations of LLMs can be fine-tuned such that these tasks can solved more accurately and if these models could perform en par with established machine learning models, which are already trained on high quality structured data. One key advantage that LLMs could have compared to classical supervised Deep Learning is their chatbox functionality, which can communicate with user questions more intuitively than a complex graphical user interface that requires structured input by the user. This type of free-text communication has the potential to improve human-machine interaction, e.g. increasing accessibility of technology for patients, in particular impaired or blind people and health professionals or researchers to information resources. The accuracy of such systems - as with all Machine Learning systems - heavily relies on previous training data that needs to be representative for the aimed task. It is assumed that ChatGPT was trained on website materials and books, thus it could amplify bias by the content creators and ignore knowledge or opinions of marginalized communities [7]Yang H. How I use ChatGPT responsibly in my teaching. Nature [Internet]. 2023 Apr 12 [cited 2023 Apr 16]; Available from: https://www.nature.com/articles/d41586-023-01026-9Google Scholar. Missing transparency has been frequently mentioned [8]ChatGPT: five priorities for research [Internet]. [cited 2023 Apr 16]. Available from: https://www.nature.com/articles/d41586-023-00288-7.Google Scholar due to the lack of information disclosed regarding the details of pre-training data used and the supervised fine-tuning tasks that lead to the remarkable performance of ChatGPT. For a specific output, ChatGPT does not provide explainability of the generation process nor does it disclose the level of its uncertainty. When faced with topics that the model has not received adequate training or supervision for, it is probable that the generated output will be fabricated, yet delivered with a strong sense of certainty, a phenomenon known as \"Artificial Hallucination\". According to OpenAI’s official website ,[9]What is ChatGPT? | OpenAI Help Center [Internet]. [cited 2023 Jun 2]. Available from: https://help.openai.com/en/articles/6783457-what-is-chatgpt.Google Scholar, information processed by ChatGPT includes the history of conversations, account details such as name and contact information. Information will be transferred from the user’s location to OpenAIs facilities and servers in the United States. Conversations can be reviewed and used for further training. Users are explicitly advised against entering sensitive information. Medical information extracted from electronic medical records should be handled with high caution and it is advisable to consult with the local IT department any use of new information technology or web services that operates outside of the care facilities. With respect to medical data safety, approaches such as federated learning are currently being discussed as possible solutions to expose ChatGPT to clinical data. While this measure may be effective to prevent protected health information to be widely disseminated, there is currently no safeguard in place to effectively monitor the quality of the learning experience and to direct the future ChatGPT output towards a verifiable and accurate level of medical information. While ChatGPT can accelerate the writing process one has to be concerned regarding fabricated output and amplification of bias. An illustrative example of Artificial Hallucination in academic writing appears when asking ChatGPT to provide literature sources for scientific statements or one of its generated answers. Provided sources are often fabricated with non-existing titles or Pubmed IDs (PMIDs) [10]Alkaissi H, McFarlane SI. Artificial hallucinations in ChatGPT: Implications in Scientific Writing. Cureus [Internet]. 2023 Feb [cited 2023 Apr 16];15(2). Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9939079/Google Scholar. Therefore, literature review and citing remains a critical part of scientific writing, which should be done manually and could still be supported by other existing interpretable IT-tools. If a significant amount of author’s text is generated via an LLM, this should be mentioned as further note or acknowledgment of the exact LLMs version. It will depend on the editorial policies of each publication organ to specify what a significant amount means. The future will show if or to which degree LLM use is acceptable at all for scientific conferences or journals. For instance, while the Science Journal [11]ChatGPT is fun, but not an author | Science [Internet]. [cited 2023 Apr 16]. Available from: https://www.science.org/doi/10.1126/science.adg7879?url_ver=Z39.88-2003&rfr_id=ori:rid:crossref.org&rfr_dat=cr_pub%20%200pubmed.Google Scholar and the International Conference for Machine Learning [12]ICML 2023 [Internet]. [cited 2023 Jun 24]. Available from: https://icml.cc/Conferences/2023/llm-policyGoogle Scholar have recently published a ban for each submission using ChatGPT or other LLMs, many other Journals are currently considering updates to their editorial policies. In our opinion, LLMs are here to stay as the aforementioned benefits and the growing use cannot be disregarded. The issues have to be taken with caution as required for any new emerging technology. An additional currently under-explored application of ChatGPT may be its utility for journal editors, reviewers and authors addressing requested revisions. As most journal editors and reviewers are facing challenges with rapidly growing numbers of submissions, future applications of LLMs may bring substantial relief for tasks requiring a high degree of effort with a low degree of expertise such as proof-reading for proper syntax, adjusting journal-specific styles and assuring semantic integrity of the submitted articles. While it should be emphasized that LLMs may never be used to replace a professional judgment call of a seasoned peer-reviewer with respect to the level of credibility and quality of the submitted original research, other highly time-consuming tasks that bear a lower-level of risk may very well be “outsourced” to LLMs if an appropriate level of supervision can be guaranteed. LLMs have enormous potential for improving communication in health care in various ways. If appropriately trained and validated, such models may excel at patient education due to their unparalleled ability to provide varying adaptable degrees of medical information to patients in an interactive iterative manner. This feature may significantly improve access to care and allow for an improved resource utilization with respect to the interactions between patients and healthcare professionals. While LLMs may never replace the doctor-patient-relationship, if properly trained, sub-specialized LLMs have the potential to become capable extenders of physicians particularly for under-served populations. From providing reader’s digest or “simple language” summaries of the most recently published research results and disease management guidelines towards assisting patients with gathering information on upcoming procedures, diagnosed conditions or management of prescriptions – the possibilities are broad. For physicians, LLMs may potentially play the role of a digital interpreter and interlocutor between increasingly complex electronic medical record systems and provide enhancements for work-flows related to note writing, report dictation, data extraction and input. LLMs may quickly become the bridge, interpreting complex or lengthy sub-specialty reports e.g. from pathology or radiology for patients and general practitioners, easing the linguistic barriers and providing language at the level requested by the end user. Generative AI and LLMs in particular are no exception to the widely debated risks of applying AI in healthcare. Aside from the aforementioned issues with Artificial Hallucination and risks of fabricated content, the black-box design of virtually all LLM algorithms hinder physicians from understanding the reasoning behind the output of the algorithm, ultimately undermining our trust in ChatGPT as a potentially useful instrument in science and clinical practice [13]Cutillo C.M. Sharma K.R. Foschini L. Kundu S. Mackintosh M. Mandl K.D. et al.Machine intelligence in healthcare—perspectives on trustworthiness, explainability, usability, and transparency.NPJ digital medicine. 2020; 3: 47Crossref PubMed Scopus (0) Google Scholar This problem has been taken serious by various national and international governing bodies, including the European Parliament. The General Data Protection Regulation and the recent AI act draft [14]Proposal for a REGULATION OF THE EUROPEAN PARLIAMENT AND OF THE COUNCIL LAYING DOWN HARMONISED RULES ON ARTIFICIAL INTELLIGENCE (ARTIFICIAL INTELLIGENCE ACT) AND AMENDING CERTAIN UNION LEGISLATIVE ACTS [Internet]. 2021. Available from: https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=celex%3A52021PC0206Google Scholar from the EU strongly endorses the right of doctors and patients to receive an explanation for results presented by AI applications, particularly in health care in which AI can be regarded as high risk application. As such, EU legislative documents suggest that black-box decision-making might violate medical ethics and undermine patient rights to autonomy and informed consent. Therefore, all applications of generative AI such as ChatGPT to clinical patient care will have to be safeguarded by mandatory elements of the algorithms assuring full transparency of the decision making [15]Reddy S. Explainability and artificial intelligence in medicine.The Lancet Digital Health. 2022; 4: e214-e215Abstract Full Text Full Text PDF PubMed Scopus (0) Google Scholar. Other regulatory aspects for AI will also remain true. As mentioned, Online LLMs should not be used for processing patient information due to privacy of sensible patient data. Even if the software version is implemented within the internal hospital network, such software will require regulatory approval when used for medical purposes. Each software technology that aims to support clinical decision making and therefore has an effect on diagnosis, treatment or prevention of disease fulfils the status as medical device. Such software, also called software as medical device (Samd), is strictly regulated in different regions e.g. by the FDA in the US or Medical Device Regulation and the IVDR in the EU. In general, AI software that aims to improve clinical decision making will require high quality and risk management during development and proven benefit while preserving patient safety before acquiring approval. As none of the LLMs are labelled as Samd, their usage should not be taken for routine clinical decision making. Moreover, health professional can be hold accountable when using such unapproved systems as is the case when administering drug agents without approval. ChatGPT has tremendous potential to improve the way how we generate or edit text and will increase accessibility of information resources. The future will generate a variety of future Large Language Models or Generative AI applications, which will be further tailored for user needs and therefore will outperform current versions in specific tasks. The technology is still at the beginning and requires critical human oversight due to amplification bias, Artificial Hallucination and the current lack of model transparency or explainability. Future developments can address these shortcomings by actively involving the scientific community, patient needs and ongoing AI regulations. Despite of their limitations, we are convinced that Large Language Models will play an important role in research activities and thus should be embraced within editorial policies and regulations.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex","attribution":"Abstract of \"ChatGPT: The transformative influence of generative AI on science and healthcare\" by Julian Varghese, Julius Chapiro, https://doi.org/10.1016/j.jhep.2023.07.028, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"arxiv:2310.19998","kind":"article","title":"Generative Retrieval-Augmented Ontologic Graph and Multiagent Strategies for Interpretive Large Language Model-Based Materials Design","authors":["Markus J. Buehler"],"author_count":1,"year":2024,"published":"2024-01-12","venue":"ACS Engineering Au","cited_by":82,"doi":"10.1021/acsengineeringau.3c00058","arxiv_id":"2310.19998","nct_id":null,"source_url":"https://doi.org/10.1021/acsengineeringau.3c00058","archive_url":"https://space-kitty.com/papers/arxiv:2310.19998","updated":"2023-10-30","pmid":"38646516","pmcid":null,"openalex_id":"W4390824394","pdf_url":"https://arxiv.org/pdf/2310.19998","abstract":"Transformer neural networks show promising capabilities, in particular for uses in materials analysis, design and manufacturing, including their capacity to work effectively with both human language, symbols, code, and numerical data. Here we explore the use of large language models (LLMs) as a tool that can support engineering analysis of materials, applied to retrieving key information about subject areas, developing research hypotheses, discovery of mechanistic relationships across disparate areas of knowledge, and writing and executing simulation codes for active knowledge generation based on physical ground truths. When used as sets of AI agents with specific features, capabilities, and instructions, LLMs can provide powerful problem solution strategies for applications in analysis and design problems. Our experiments focus on using a fine-tuned model, MechGPT, developed based on training data in the mechanics of materials domain. We first affirm how finetuning endows LLMs with reasonable understanding of domain knowledge. However, when queried outside the context of learned matter, LLMs can have difficulty to recall correct information. We show how this can be addressed using retrieval-augmented Ontological Knowledge Graph strategies that discern how the model understands what concepts are important and how they are related. Illustrated for a use case of relating distinct areas of knowledge - here, music and proteins - such strategies can also provide an interpretable graph structure with rich information at the node, edge and subgraph level. We discuss nonlinear sampling strategies and agent-based modeling applied to complex question answering, code generation and execution in the context of automated force field development from actively learned Density Functional Theory (DFT) modeling, and data analysis.","abstract_license":"CC0-1.0 (arXiv descriptive metadata)","license":"cc-by-nc-nd","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Machine Learning in Materials Science"],"details":null,"provenance":"openalex+arxiv","attribution":"Abstract: arXiv descriptive metadata (CC0). Thank you to arXiv for use of its open access interoperability. This service was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv."},{"id":"doi:10.1111/bjet.13607","kind":"article","title":"Human– AI collaborative learning in mixed reality: Examining the cognitive and socio‐emotional interactions","authors":["Belle Dang","Thu-Nguyet Huynh","Faaiz Gul","Carolyn Penstein Rosé","Sanna Järvelä","Andy Nguyen"],"author_count":6,"year":2025,"published":"2025-06-05","venue":"British Journal of Educational Technology","cited_by":73,"doi":"10.1111/bjet.13607","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1111/bjet.13607","archive_url":"https://space-kitty.com/papers/doi:10.1111/bjet.13607","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4411066932","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/bjet.13607","abstract":"The rise of generative artificial intelligence (GAI), especially with multimodal large language models like GPT‐4o, sparked transformative potential and challenges for learning and teaching. With potential as a cognitive offloading tool, GAI can enable learners to focus on higher‐order thinking and creativity. Yet, this also raises questions about integration into traditional education due to the limited research on learners' interactions with GAI. Some studies with GAI focus on text‐based human–AI interactions, while research on embodied GAI in immersive environments like mixed reality (MR) remains unexplored. To address this, this study investigates interaction dynamics between learners and embodied GAI agents in MR, examining cognitive and socio‐emotional interactions during collaborative learning. We investigated the paired interactive patterns between a student and an embodied GAI agent in MR, based on data from 26 higher education students with 1317 recorded activities. Data were analysed using a multi‐layered learning analytics approach, including quantitative content analysis, sequence analysis via hierarchical clustering and pattern analysis through ordered network analysis (ONA). Our findings identified two interaction patterns: type (1) AI‐led Supported Exploratory Questioning (AISQ) and type (2) Learner‐Initiated Inquiry (LII) group. Despite their distinction in characteristic, both types demonstrated comparable levels of socio‐emotional engagement and exhibited meaningful cognitive engagement, surpassing the superficial content reproduction that can be observed in interactions with GPT models. This study contributes to the human–AI collaboration and learning studies, extending understanding to learning in MR environments and highlighting implications for designing AI‐based educational tools. Practitioner notes What is already known about this topic Socio‐emotional interactions are fundamental to cognitive processes and play a critical role in collaborative learning. Generative artificial intelligence (GAI) holds transformative potential for education but raises questions about how learners interact with such technology. Most existing research focuses on text‐based interactions with GAI; there is limited empirical evidence on how embodied GAI agents within immersive environments like Mixed Reality (MR) influence the cognitive and socio‐emotional interactions for learning and regulation. What this paper adds Provides first empirical insights into cognitive and socio‐emotional interaction patterns between learners and embodied GAI agents in MR environments. Identifies two distinct interaction patterns: AISQ type (structured, guided, supportive) and LII type (inquiry‐driven, exploratory, engaging), demonstrating how these patterns influence collaborative learning dynamics. Shows that both interaction types facilitate meaningful cognitive engagement, moving beyond superficial content reproduction commonly associated with GAI interactions. Implications for practice and/or policy Insights from the identified interaction patterns can inform the design of teaching strategies that effectively integrate embodied GAI agents to enhance both cognitive and socio‐emotional engagement. Findings can guide the development of AI‐based educational tools that capitalise on the capabilities of embodied GAI agents, supporting a balance between structured guidance and exploratory learning. Highlights the need for ethical considerations in adopting embodied GAI agents, particularly regarding the human‐like realism of these agents and potential impacts on learner dependency and interaction norms.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Intelligent Tutoring Systems and Adaptive Learning"],"details":null,"provenance":"openalex","attribution":"Abstract of \"Human– AI collaborative learning in mixed reality: Examining the cognitive and socio‐emotional interactions\" by Belle Dang, Thu-Nguyet Huynh, Faaiz Gul et al., https://doi.org/10.1111/bjet.13607, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"doi:10.1016/j.enbuild.2024.114691","kind":"article","title":"Exploring automated energy optimization with unstructured building data: A multi-agent based framework leveraging large language models","authors":["Tong Xiao","Peng Xu"],"author_count":2,"year":2024,"published":"2024-08-23","venue":"Energy and Buildings","cited_by":81,"doi":"10.1016/j.enbuild.2024.114691","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.enbuild.2024.114691","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.enbuild.2024.114691","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4401818274","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Building Energy and Comfort Optimization"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"doi:10.3390/a18080499","kind":"article","title":"A Research Landscape of Agentic AI and Large Language Models: Applications, Challenges and Future Directions","authors":["Sarfraz Nawaz Brohi","Qurat-ul-ain Mastoi","Noor Zaman Jhanjhi","Thulasyammal Ramiah Pillai"],"author_count":4,"year":2025,"published":"2025-08-11","venue":"Algorithms","cited_by":68,"doi":"10.3390/a18080499","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.3390/a18080499","archive_url":"https://space-kitty.com/papers/doi:10.3390/a18080499","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4413222071","pdf_url":null,"abstract":"Agentic AI and Large Language Models (LLMs) are transforming how language is understood and generated while reshaping decision-making, automation, and research practices. LLMs provide underlying reasoning capabilities, and Agentic AI systems use them to perform tasks through interactions with external tools, services, and Application Programming Interfaces (APIs). Based on a structured scoping review and thematic analysis, this study identifies that core challenges of LLMs, relating to security, privacy and trust, misinformation, misuse and bias, energy consumption, transparency and explainability, and value alignment, can propagate into Agentic AI. Beyond these inherited concerns, Agentic AI introduces new challenges, including context management, security, privacy and trust, goal misalignment, opaque decision-making, limited human oversight, multi-agent coordination, ethical and legal accountability, and long-term safety. We analyse the applications of Agentic AI powered by LLMs across six domains: education, healthcare, cybersecurity, autonomous vehicles, e-commerce, and customer service, to reveal their real-world impact. Furthermore, we demonstrate some LLM limitations using DeepSeek-R1 and GPT-4o. To the best of our knowledge, this is the first comprehensive study to integrate the challenges and applications of LLMs and Agentic AI within a single forward-looking research landscape that promotes interdisciplinary research and responsible advancement of this emerging field.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Ethics and Social Impacts of AI"],"details":null,"provenance":"openalex","attribution":"Abstract of \"A Research Landscape of Agentic AI and Large Language Models: Applications, Challenges and Future Directions\" by Sarfraz Nawaz Brohi, Qurat-ul-ain Mastoi, Noor Zaman Jhanjhi et al., https://doi.org/10.3390/a18080499, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"doi:10.1056/aidbp2500144","kind":"article","title":"MedAgentBench: A Virtual EHR Environment to Benchmark Medical LLM Agents","authors":["Yixing Jiang","Kameron Collin Black","Gloria Geng","Danny Park","James Zou","Andrew Y. Ng","Jonathan H. Chen"],"author_count":7,"year":2025,"published":"2025-08-14","venue":"NEJM AI","cited_by":66,"doi":"10.1056/aidbp2500144","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1056/aidbp2500144","archive_url":"https://space-kitty.com/papers/doi:10.1056/aidbp2500144","updated":null,"pmid":"42932685","pmcid":null,"openalex_id":"W4413801638","pdf_url":"https://ai.nejm.org/doi/pdf/10.1056/AIdbp2500144","abstract":null,"abstract_license":null,"license":null,"is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"doi:10.1093/jxb/erz175","kind":"article","title":"Plant and crop simulation models: powerful tools to link physiology, genetics, and phenomics","authors":["Bertrand Muller","Pierre Martre"],"author_count":2,"year":2019,"published":"2019-04-11","venue":"Journal of Experimental Botany","cited_by":106,"doi":"10.1093/jxb/erz175","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1093/jxb/erz175","archive_url":"https://space-kitty.com/papers/doi:10.1093/jxb/erz175","updated":null,"pmid":"31091319","pmcid":null,"openalex_id":"W2943202724","pdf_url":"https://academic.oup.com/jxb/article-pdf/70/9/2339/28540500/erz175.pdf","abstract":null,"abstract_license":null,"license":null,"is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Crop Yield and Soil Fertility"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0)."},{"id":"doi:10.1080/17538947.2025.2497489","kind":"article","title":"GIS Copilot: towards an autonomous GIS agent for spatial analysis","authors":["Temitope Akinboyewa","Zhenlong Li","Huan Ning","M. Naser Lessani"],"author_count":4,"year":2025,"published":"2025-04-28","venue":"International Journal of Digital Earth","cited_by":64,"doi":"10.1080/17538947.2025.2497489","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1080/17538947.2025.2497489","archive_url":"https://space-kitty.com/papers/doi:10.1080/17538947.2025.2497489","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4409881395","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/17538947.2025.2497489?needAccess=true","abstract":"Recent advancements in generative artificial intelligence (AI), particularly Large Language Models (LLMs), offer promising capabilities for spatial analysis. However, their integration with established GIS platforms remains underexplored. In this study, we propose a framework that embeds LLMs into existing GIS platforms, using QGIS as a case study. Our approach leverages LLMs’ reasoning and coding abilities to autonomously generate spatial analysis workflows through an informed agent equipped with comprehensive documentation of key GIS tools and parameters. External tools such as GeoPandas are also incorporated to enhance the system's geoprocessing capabilities. Based on this framework, we developed a ‘GIS Copilot’ that enables users to interact with QGIS using natural language. We evaluated the copilot across over 100 tasks of varying complexity including basic (single tool/layer), intermediate (multistep with guidance), and advanced (multistep without guidance). Results show high success rates for basic and intermediate tasks, with challenges remaining in fully autonomous execution of advanced tasks. The GIS Copilot advances the vision of autonomous GIS by enabling non-experts to perform geospatial analysis with minimal prior knowledge. While full autonomy is not yet achieved, the copilot demonstrates significant potential for simplifying GIS workflows and enhancing decision-making processes.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Geographic Information Systems Studies"],"details":null,"provenance":"openalex","attribution":"Abstract of \"GIS Copilot: towards an autonomous GIS agent for spatial analysis\" by Temitope Akinboyewa, Zhenlong Li, Huan Ning et al., https://doi.org/10.1080/17538947.2025.2497489, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified."},{"id":"arxiv:2506.04133","kind":"article","title":"TRiSM for Agentic AI: A review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems","authors":["Shaina Raza","Ranjan Sapkota","Manoj Karkee","Christos Emmanouilidis"],"author_count":4,"year":2026,"published":"2026-01-01","venue":"AI Open","cited_by":55,"doi":"10.1016/j.aiopen.2026.02.006","arxiv_id":"2506.04133","nct_id":null,"source_url":"https://doi.org/10.1016/j.aiopen.2026.02.006","archive_url":"https://space-kitty.com/papers/arxiv:2506.04133","updated":"2025-12-18","pmid":null,"pmcid":null,"openalex_id":"W7133236347","pdf_url":"https://arxiv.org/pdf/2506.04133","abstract":"Agentic AI systems, built upon large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligence, autonomy, collaboration, and decision-making across enterprise and societal domains. This review presents a structured analysis of Trust, Risk, and Security Management (TRiSM) in the context of LLM-based Agentic Multi-Agent Systems (AMAS). We begin by examining the conceptual foundations of Agentic AI and highlight its architectural distinctions from traditional AI agents. We then adapt and extend the AI TRiSM framework for Agentic AI, structured around key pillars: \\textit{ Explainability, ModelOps, Security, Privacy} and \\textit{their Lifecycle Governance}, each contextualized to the challenges of AMAS. A risk taxonomy is proposed to capture the unique threats and vulnerabilities of Agentic AI, ranging from coordination failures to prompt-based adversarial manipulation. To support practical assessment in Agentic AI works, we introduce two novel metrics: the Component Synergy Score (CSS), which quantifies the quality of inter-agent collaboration, and the Tool Utilization Efficacy (TUE), which evaluates the efficiency of tool use within agent workflows. We further discuss strategies for improving explainability in Agentic AI, as well as approaches to enhancing security and privacy through encryption, adversarial robustness, and regulatory compliance. The review concludes with a research roadmap for the responsible development and deployment of Agentic AI, highlighting key directions to align emerging systems with TRiSM principles-ensuring safety, transparency, and accountability in their operation.","abstract_license":"CC0-1.0 (arXiv descriptive metadata)","license":"cc-by-nc-nd","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Ethics and Social Impacts of AI"],"details":null,"provenance":"openalex+arxiv","attribution":"Abstract: arXiv descriptive metadata (CC0). Thank you to arXiv for use of its open access interoperability. This service was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv."}],"next":"https://space-kitty.com/api/v1/topics/ai-agents/papers?sort=top&limit=25&offset=25"}