mlsanityData to 7 Oct 2026

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

arXiv 2310.04406 ↗First posted 6 Oct 2023cs.AI cs.CL cs.CVcited by 551

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of LMs in reasoning, acting, and planning. By leveraging the in-context learning ability of LMs, we integrate Monte Carlo Tree Search into LATS to enable LMs as agents, along with LM-powered value functions and self-reflections for proficient exploration and enhanced decision-making. A key feature of our approach is the incorporation of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism that surpasses the constraints of existing techniques. Our experimental evaluation across diverse domains, including programming, interactive question-answering (QA), web navigation, and math, validates the effectiveness and generality of LATS in decision-making while maintaining competitive or improved reasoning performance. Notably, LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT-3.5. Code can be found at https://github.com/lapisrocks/LanguageAgentTreeSearch

Key facts. Cited by 551 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 57 of its 84 references that are in the map. First posted on arXiv 6 Oct 2023.

Builds on

57 of 84 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency29 Sep
  2. 2023Reasoning with Language Model is Planning with World Model24 May

Other references · 55

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  9. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  11. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  12. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
38 more
  1. 2021Program Synthesis with Large Language Modelscited by 3,509
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  5. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  6. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  8. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  10. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  11. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  12. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  13. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  14. 2023Mastering Diverse Domains through World Modelscited by 1,193
  15. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  16. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  17. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  18. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  19. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  20. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  21. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  22. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  23. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  24. 2022PAL: Program-aided Language Modelscited by 635
  25. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  26. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  27. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
  28. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  29. 2022CodeT: Code Generation with Generated Testscited by 369
  30. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  31. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  32. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  33. 2018Reinforcement Learning on Web Interfaces Using Workflow-Guided Explorationcited by 282
  34. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
  35. 2021Mastering Atari Games with Limited Datacited by 235
  36. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 210
  37. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  38. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 159

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 99; 2025: 170; 2026: 272.

551 papers.

Sort:

By area:

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  2. 2025s1: Simple test-time scalingcited by 1,311
  3. 2024A Survey on Large Language Models for Code Generationcited by 646
  4. 2023AppAgent: Multimodal Agents as Smartphone Userscited by 407
  5. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  6. 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 289
  7. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 282
  8. 2025TTRL: Test-Time Reinforcement Learningcited by 253
  9. 2024AI Agents That Mattercited by 199
  10. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  11. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  12. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 162
38 more
  1. 2024The BrowserGym Ecosystem for Web Agent Researchcited by 152
  2. 2024Tree Search for Language Model Agentscited by 148
  3. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  5. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 123
  6. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 120
  7. 2024AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agentscited by 110
  8. 2025Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thoughtcited by 108
  9. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 102
  10. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  11. 2024GUI Agents: A Surveycited by 101
  12. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Explorationcited by 100
  13. 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Designcited by 100
  14. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 93
  15. 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agentscited by 87
  16. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  17. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  18. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  19. 2024DebugBench: Evaluating Debugging Capability of Large Language Modelscited by 74
  20. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  21. 2025Tree Search for LLM Agent Reinforcement Learningcited by 73
  22. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  23. 2024Can Language Models Solve Olympiad Programming?cited by 70
  24. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  25. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 62
  26. 2024ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learningcited by 61
  27. 2025A Survey on (M)LLM-Based GUI Agentscited by 61
  28. 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agentscited by 59
  29. 2025Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifierscited by 58
  30. 2025Efficient Inference for Large Reasoning Models: A Surveycited by 58
  31. 2025WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Modelcited by 56
  32. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  33. 2024AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learningcited by 52
  34. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTScited by 52
  35. 2025AgentRefine: Enhancing Agent Generalization through Refinement Tuningcited by 51
  36. 2024MASAI: Modular Architecture for Software-engineering AI Agentscited by 49
  37. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 49
  38. 2024Autoformulation of Mathematical Optimization Models Using LLMscited by 48

50 most cited of 551 All 551 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Policy Guided Tree Search for Enhanced LLM Reasoning
  2. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
  3. 2026Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents
  4. 2026The Context Gathering Decision Process: A POMDP Framework for Agentic Search
  5. 2026Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns
  6. 2025Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning
  7. 2026Policy-Guided Search on Tree-of-Thoughts for Efficient Problem Solving with Bounded Language Model Queries
  8. 2026AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments