mlsanityData to 14 Oct 2026

ADaPT: As-Needed Decomposition and Planning with Language Models

arXiv 2311.05772 ↗First posted 8 Nov 2023cs.AI cs.CL cs.LGcited by 177

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

Abstract (arXiv)

Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two ways: iteratively determining the next action (iterative executors) or generating plans and executing sub-tasks using LLMs (plan-and-execute). However, these methods struggle with task complexity, as the inability to execute any sub-task may lead to task failure. To address these shortcomings, we introduce As-Needed Decomposition and Planning for complex Tasks (ADaPT), an approach that explicitly plans and decomposes complex sub-tasks as-needed, i.e., when the LLM is unable to execute them. ADaPT recursively decomposes sub-tasks to adapt to both task complexity and LLM capability. Our results demonstrate that ADaPT substantially outperforms established strong baselines, achieving success rates up to 28.3% higher in ALFWorld, 27% in WebShop, and 33% in TextCraft -- a novel compositional dataset that we introduce. Through extensive analysis, we illustrate the importance of multilevel decomposition and establish that ADaPT dynamically adjusts to the capabilities of the executor LLM as well as to task complexity.

Key facts. Cited by 177 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 44 of its 83 references that are in the map. First posted on arXiv 8 Nov 2023.

Builds on

44 of 83 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May

Other references · 43

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  10. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  11. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  12. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
31 more
  1. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  2. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  3. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  4. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  5. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 503
  6. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  7. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 455
  8. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  9. 2015Neural Module Networkscited by 376
  10. 2018TextWorld: A Learning Environment for Text-based Gamescited by 310
  11. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 251
  12. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 238
  13. 2021FILM: Following Instructions in Language with Modular Methodscited by 121
  14. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  15. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  16. 2022Language Model Cascadescited by 107
  17. 2021Skill Induction and Planning with Latent Languagecited by 99
  18. 2021A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Executioncited by 91
  19. 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 89
  20. 2023Lemur: Harmonizing Natural Language and Code for Language Agentscited by 72
  21. 2019Neural Module Networks for Reasoning over Textcited by 66
  22. 2020Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Modelscited by 65
  23. 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
  24. 2021Hierarchical Reinforcement Learning By Discovering Intrinsic Optionscited by 58
  25. 2022Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstrationcited by 54
  26. 2019Learning to Infer Program Sketchescited by 44
  27. 2021Wordcraft: a Human-AI Collaborative Editor for Story Writingcited by 41
  28. 2019Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoningcited by 28
  29. 2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generationcited by 27
  30. 2022Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Treescited by 14
  31. 2014An Overview of Hierarchical Task Network Planningcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 38; 2025: 74; 2026: 63.

177 papers.

Sort:

By area:

  1. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  2. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 223
  3. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 195
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  5. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  6. 2024AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agentscited by 114
  7. 2024A Survey on Large Language Model-Based Game Agentscited by 112
  8. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Explorationcited by 101
  9. 2024DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agentscited by 100
  10. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 83
  11. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 83
  12. 2025Agent-R: Training Language Model Agents to Reflect via Iterative Self-Trainingcited by 82
38 more
  1. 2024RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agentscited by 80
  2. 2024A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasonerscited by 73
  3. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 72
  4. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  5. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  6. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 57
  7. 2024Learning to Use Tools via Cooperative and Interactive Agentscited by 54
  8. 2024TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generationcited by 51
  9. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  10. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 40
  11. 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractionscited by 36
  12. 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agentscited by 36
  13. 2024System-1.x: Learning to Balance Fast and Slow Planning with Language Modelscited by 35
  14. 2024Data-driven Discovery with Large Generative Modelscited by 34
  15. 2025Flow: Modularized Agentic Workflow Automationcited by 34
  16. 2024LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environmentscited by 32
  17. 2025ATLaS: Agent Tuning via Learning Critical Stepscited by 31
  18. 2025Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Gamescited by 31
  19. 2025TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Reviewcited by 31
  20. 2025We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systemscited by 27
  21. 2024Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skillscited by 26
  22. 2024Soft Self-Consistency Improves Language Model Agentscited by 25
  23. 2024THREAD: Thinking Deeper with Recursive Spawningcited by 25
  24. 2023Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planningcited by 24
  25. 2023Creative Agents: Empowering Agents with Imagination for Creative Taskscited by 24
  26. 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-trackingcited by 23
  27. 2025Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executorscited by 22
  28. 2024SelfGoal: Your Language Agents Already Know How to Achieve High-level Goalscited by 21
  29. 2025TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planningcited by 21
  30. 2025The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvementcited by 20
  31. 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environmentscited by 18
  32. 2025Build the web for agents, not agents for the webcited by 18
  33. 2024Devil's Advocate: Anticipatory Reflection for LLM Agentscited by 17
  34. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 16
  35. 2024Plancraft: an evaluation dataset for planning with LLM agentscited by 16
  36. 2025Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structurescited by 16
  37. 2025Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Modelscited by 16
  38. 2025Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planningcited by 15

50 most cited of 177 All 177 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change
  2. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models
  3. 2026PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models
  4. 2025Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning
  5. 2026AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
  6. 2025On the Limits of Innate Planning in Large Language Models
  7. 2025Efficient LLM Collaboration via Planning
  8. 2023Tree-Planner: Efficient Close-loop Task Planning with Large Language Models