LLM Agents & Tool Use

Agents, tool/API use, planning and acting with language models.

A topic in the Science corpus, drawn from 185 papers.

Trusted voices in LLM Agents & Tool Use

Ordered by the trust LLM Agents & Tool Use's own network concentrates on each researcher, most first.

  1. Pieter Abbeel — trusted by 105 researchers here
  2. Igor Mordatch — trusted by 105 researchers here
  3. Malte Helmert — trusted by 85 researchers here
  4. Yedid Hoshen — trusted by 62 researchers here
  5. Bernhard Nebel — trusted by 52 researchers here
  6. Jörg Hoffmann — trusted by 51 researchers here
  7. Arthur Szlam — trusted by 53 researchers here
  8. Rob Fergus — trusted by 52 researchers here
  9. Sainbayar Sukhbaatar — trusted by 51 researchers here
  10. Alessandro Sordoni — trusted by 36 researchers here
  11. Aaron C. Courville — trusted by 36 researchers here
  12. Yoshua Bengio — trusted by 35 researchers here

Most-cited papers in LLM Agents & Tool Use

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. ReAct: Synergizing Reasoning and Acting in Language Models (2022, International Conference on Learning Representations) — 8,935 citations
  2. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (2017) — 6,086 citations
  3. Toolformer: Language Models Can Teach Themselves to Use Tools (2023, Neural Information Processing Systems) — 4,753 citations
  4. Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022) — 3,376 citations
  5. The FF Planning System: Fast Plan Generation Through Heuristic Search (2011) — 2,435 citations
  6. The Fast Downward Planning System (2006) — 2,109 citations
  7. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs (2023) — 1,907 citations
  8. Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (2015) — 1,811 citations
  9. Code as Policies: Language Model Programs for Embodied Control (2022) — 1,688 citations
  10. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools (2024) — 1,646 citations
  11. Cooperative Multi-Agent Learning: The State of the Art (2005) — 1,452 citations
  12. Inner Monologue: Embodied Reasoning through Planning with Language Models (2022) — 1,446 citations
  13. Gorilla: Large Language Model Connected with Massive APIs (2023) — 1,419 citations
  14. Learning Multiagent Communication with Backpropagation (2016) — 1,366 citations
  15. The StarCraft Multi-Agent Challenge (2019) — 1,262 citations
  16. A Generalist Agent (2022) — 1,117 citations
  17. OpenAssistant Conversations - Democratizing Large Language Model Alignment (2023) — 893 citations
  18. Emergence of Grounded Compositional Language in Multi-Agent Populations (2017) — 815 citations
  19. CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing (2023) — 809 citations
  20. The Design and Implementation of XiaoIce, an Empathetic Social Chatbot (2018) — 748 citations
  21. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts (2021) — 679 citations
  22. Learning Attentional Communication for Multi-Agent Cooperation (2018) — 609 citations
  23. MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action (2023) — 603 citations
  24. Human-level play in the game of Diplomacy by combining language models with strategic reasoning (2022) — 592 citations
  25. Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents (2023) — 502 citations
  26. Walk the Talk: Connecting Language, Knowledge, and Action in Route Instructions (2006) — 431 citations
  27. Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration (2018) — 349 citations
  28. OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs (2019) — 346 citations
  29. World of Bits: An Open-Domain Platform for Web-Based Agents (2017) — 341 citations
  30. Reflexion: an autonomous agent with dynamic memory and self-reflection (2023) — 338 citations
  31. Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models (2020) — 326 citations
  32. ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving (2023) — 314 citations
  33. PromptChainer: Chaining Large Language Model Prompts through Visual Programming (2022) — 301 citations
  34. Conversational AI: The Science Behind the Alexa Prize (2018) — 301 citations
  35. BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage (2022) — 297 citations
  36. OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement (2024) — 279 citations
  37. Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning (2023) — 272 citations
  38. Jigsaw: Large Language Models meet Program Synthesis (2021) — 257 citations
  39. Open-vocabulary Queryable Scene Representations for Real World Planning (2022) — 257 citations
  40. VAIN: Attentional Multi-agent Predictive Modeling (2017) — 255 citations
  41. Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences (2015) — 247 citations
  42. Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks (2019) — 232 citations
  43. Alignment of Language Agents (2021) — 227 citations
  44. Coordinated Multi-Agent Imitation Learning (2017) — 212 citations
  45. Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings (2017) — 210 citations
  46. TALM: Tool Augmented Language Models (2022) — 207 citations
  47. TAMER: Training an Agent Manually via Evaluative Reinforcement (2008) — 204 citations
  48. Learning to Interpret Natural Language Commands through Human-Robot Dialog (2015) — 200 citations
  49. An effective personal mobile robot agent through symbiotic human-robot interaction (2010) — 200 citations
  50. Explainable Agency for Intelligent Autonomous Systems (2017) — 198 citations

Most active researchers

By papers in this topic: a volume measure, not trust.