mlsanityData to 7 Oct 2026

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

arXiv 2305.18323 ↗First posted 23 May 2023cs.CL cs.AIcited by 174

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) with tools that allow for knowledge retrieval and action execution. Existing ALM systems trigger LLM thought processes while pulling observations from these tools in an interleaved fashion. Specifically, an LLM reasons to call an external tool, gets halted to fetch the tool's response, and then decides the next action based on all preceding response tokens. Such a paradigm, though straightforward and easy to implement, often leads to huge computation complexity from redundant prompts and repeated execution. This study addresses such challenges for the first time, proposing a modular paradigm ReWOO (Reasoning WithOut Observation) that detaches the reasoning process from external observations, thus significantly reducing token consumption. Comprehensive evaluations across six public NLP benchmarks and a curated dataset reveal consistent performance enhancements with our proposed methodology. Notably, ReWOO achieves 5x token efficiency and 4% accuracy improvement on HotpotQA, a multi-step reasoning benchmark. Furthermore, ReWOO demonstrates robustness under tool-failure scenarios. Beyond prompt efficiency, decoupling parametric modules from non-parametric tool calls enables instruction fine-tuning to offload LLMs into smaller language models, thus substantially reducing model parameters. Our illustrative work offloads reasoning ability from 175B GPT3.5 into 7B LLaMA, demonstrating the significant potential for truly efficient and scalable ALM systems.

Key facts. Cited by 174 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 34 of its 41 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

34 of 41 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb
  2. 2023Augmented Language Models: a Survey15 Feb
  3. 2023Specializing Smaller Language Models towards Multi-Step Reasoning30 Jan
  4. 2022PAL: Program-aided Language Models18 Nov
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Models6 Oct

Other references · 29

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  10. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  12. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
17 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  2. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  3. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 863
  4. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  5. 2023Instruction Tuning with GPT-4cited by 676
  6. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  7. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  8. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  9. 2023Language Models can Solve Computer Taskscited by 371
  10. 2023Tool Learning with Foundation Modelscited by 302
  11. 2023ChatGPT for Robotics: Design Principles and Model Abilitiescited by 296
  12. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 278
  13. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 193
  14. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  15. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  16. 2022Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Modelscited by 96
  17. 2023Batch Prompting: Efficient Inference with Large Language Model APIscited by 84

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 24; 2024: 47; 2025: 37; 2026: 66.

174 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2024Large Language Models: A Surveycited by 506
  4. 2023Cognitive Architectures for Language Agentscited by 422
  5. 2023Orca: Progressive Learning from Complex Explanation Traces of GPT-4cited by 369
  6. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  7. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 319
  8. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  9. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 180
  10. 2023An LLM Compiler for Parallel Function Callingcited by 170
  11. 2023Text2Reward: Reward Shaping with Language Models for Reinforcement Learningcited by 153
  12. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 136
38 more
  1. 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Taskscited by 134
  2. 2023Large Language Models for Robotics: A Surveycited by 132
  3. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  4. 2024BadAgent: Inserting and Activating Backdoor Attacks in LLM Agentscited by 106
  5. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 97
  6. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 91
  7. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agentscited by 83
  8. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  9. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
  10. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  11. 2023Lemur: Harmonizing Natural Language and Code for Language Agentscited by 71
  12. 2024OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automationcited by 66
  13. 2024Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agentcited by 65
  14. 2024Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysiscited by 60
  15. 2024AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectoriescited by 56
  16. 2024AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent Systemcited by 53
  17. 2024Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Taskscited by 52
  18. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  19. 2024Prompt Design and Engineering: Introduction and Advanced Methodscited by 45
  20. 2024API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMscited by 39
  21. 2024OSCAR: Operating System Control via State-Aware Reasoning and Re-Planningcited by 37
  22. 2024Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agentscited by 35
  23. 2024Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Modelscited by 34
  24. 2024Thought of Search: Planning with Language Models Through The Lens of Efficiencycited by 32
  25. 2023Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoningcited by 30
  26. 2025AutoPDL: Automatic Prompt Optimization for LLM Agentscited by 27
  27. 2023Gentopia: A Collaborative Platform for Tool-Augmented LLMscited by 25
  28. 2024AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedbackcited by 25
  29. 2024AppBench: Planning of Multiple APIs from Various APPs for Complex User Instructioncited by 24
  30. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23
  31. 2023Adapting LLM Agents with Universal Feedback in Communicationcited by 19
  32. 2025D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Securitycited by 19
  33. 2024Asynchronous LLM Function Callingcited by 18
  34. 2026Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learnedcited by 18
  35. 2024Devil's Advocate: Anticipatory Reflection for LLM Agentscited by 17
  36. 2025Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPOcited by 17
  37. 2026SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystemscited by 17
  38. 2024Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Executioncited by 16

50 most cited of 174 All 174 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models
  2. 2025SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
  3. 2026Maistros: A Greek Large Language Model Adapted Through Knowledge Distillation From Large Reasoning Models
  4. 2025mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning
  5. 2023Re-Reading Improves Reasoning in Large Language Models
  6. 2024Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving
  7. 2024Information Re-Organization Improves Reasoning in Large Language Models
  8. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Review