LLM Agents & Tool-Augmented Language Models Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Large language models become agents when they can reason, act, and call tools. This list collects the papers that defined ReAct, tool learning, and long-horizon agent behavior.

LLM Agents & Tool-Augmented Language Models: 10 key papers

1. ReAct: Synergizing Reasoning and Acting in Language Models
   Yao et al. arXiv 2022.
2. Toolformer: Language Models Can Teach Themselves to Use Tools
   Schick et al. arXiv 2023.
3. Reflexion: Language Agents with Verbal Reinforcement Learning
   Shinn et al. arXiv 2023.
4. Generative Agents: Interactive Simulacra of Human Behavior
   Park et al. arXiv 2023.
5. Voyager: An Open-Ended Embodied Agent with Large Language Models
   Wang et al. arXiv 2023.
6. AgentBench: Evaluating LLMs as Agents
   Liu et al. arXiv 2023.
7. WebArena: A Realistic Web Environment for Building Autonomous Agents
   Zhou et al. arXiv 2023.
8. The Rise and Potential of Large Language Model Based Agents: A Survey
   Xi et al. arXiv 2023.
9. Inner Monologue: Embodied Reasoning through Planning with Language Models
   Huang et al. arXiv 2022.
10. Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
    Ahn et al. arXiv 2022.

Related reading lists

• Reasoning in LLMs
• Chain-of-Thought & Reasoning
• Prompt Optimization & In-Context Learning for LLMs
• Quantization for Efficient Inference
• Causal Inference & RL
• Unsupervised Environment Design
• Swarm RL & Collective Behavior
• RL from Human Feedback (RLHF)