LLM Agents & Tool Use
Agents that plan and act: tool and function calling, computer-use and coding agents, multi-agent systems, agent benchmarks and agent protocols.
Most influential
- Augmenting large language models with chemistry tools
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 …
Abstract excerpt by Andres M Bran et al., CC-BY, https://doi.org/10.1038/s42256-024-00832-8; truncated.
Article792 citationsdoi:10.1038/s42256-024-00832-8 - Empowering biomedical discovery with AI agents
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 ana…
Review315 citationsarXiv:2404.02831doi:10.1016/j.cell.2024.09.022 - 2004, “From System Dynamics and Discrete Event to Practical Agent Based Modeling: Reasons, Techniques, ToolsArticle501 citations
- CRISPR-GPT for agentic automation of gene-editing experiments
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…
Article146 citationsarXiv:2404.18021doi:10.1038/s41551-025-01463-z - Large language models for reticular chemistryReview134 citationsdoi:10.1038/s41578-025-00772-8
- Biomni: A General-Purpose Biomedical AI Agent
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 i…
Abstract excerpt by Kexin Huang et al., CC-BY, https://doi.org/10.1101/2025.05.30.656746; truncated.
Article124 citationsdoi:10.1101/2025.05.30.656746 - Potential and Pitfalls of ChatGPT and Natural-Language Artificial Intelligence Models for Diabetes EducationArticle160 citationsdoi:10.2337/dc23-0197
- Demystifying LLM-Based Software Engineering Agents
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 equip…
Abstract excerpt by Chunqiu Steven Xia et al., CC-BY, https://doi.org/10.1145/3715754; truncated.
Article115 citationsdoi:10.1145/3715754 - Parallel agent-based simulation with Repast for High Performance ComputingArticle215 citationsdoi:10.1177/0037549712462620
- Large Language Model Enhanced Multi-Agent Systems for 6G Communications
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, li…
Article123 citationsarXiv:2312.07850doi:10.1109/mwc.016.2300600 - Emergent Tool Use From Multi-Agent Autocurricula
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 age…
Preprint424 citationsarXiv:1909.07528 - Optimizing generative AI by backpropagating language model feedbackArticle85 citationsdoi:10.1038/s41586-025-08661-4
- Survey of Agent Based Modelling and Simulation Tools
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 techniq…
Abstract excerpt by RJ Allan, CC-BY, https://doi.org/10.5286/dltr.2010007; truncated.
Article159 citationsdoi:10.5286/dltr.2010007 - Large language models for chemistry robotics
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 sys…
Abstract excerpt by Naruki Yoshikawa et al., CC-BY, https://doi.org/10.1007/s10514-023-10136-2; truncated.
Article112 citationsdoi:10.1007/s10514-023-10136-2 - Evaluating large language models and agents in healthcare: key challenges in clinical applicationsArticle75 citationsdoi:10.1016/j.imed.2025.03.002
Newest work
- Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AIPreprintarXiv:2610.38095
- El Agente Quntur: Agentic Active-Space Selection for CASSCFPreprintarXiv:2610.38145
- DecompGym: Benchmarking LLM Agents on Designing Decomposition AlgorithmsPreprintarXiv:2610.38175
- Disparity Laundering: Consensus Without Fairness in Clinical Multi-Agent SystemsPreprintarXiv:2610.38215
- FACTS-MAS: A Multi-Agent Architecture for Adaptive Forecasting from Heterogeneous EvidencePreprintarXiv:2610.38225
- Vendster: An Evaluation Arena to Investigate How Forecasting Tool Quality Affects LLM Agent Behaviors in Buyer-Vendor NegotiationPreprintarXiv:2610.38292
- EPSBench: Benchmarking LLM Agents for Earnings ForecastingPreprintarXiv:2610.38293
- LASSO: An LLM-Agent Synthesized System for SQL ValidationPreprintarXiv:2610.38294
- A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI AcceleratorPreprintarXiv:2610.38329
- SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement LearningPreprintarXiv:2610.38391