mlsanityData to 14 Oct 2026

Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks

arXiv 2503.09572 ↗First posted 12 Mar 2025cs.CLcited by 195

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tasks remains a challenge. Recent work have found success by separating high-level planning from low-level execution, which enables the model to effectively balance high-level planning objectives and low-level execution details. However, generating accurate plans remains difficult since LLMs are not inherently trained for this task. To address this, we propose Plan-and-Act, a novel framework that incorporates explicit planning into LLM-based agents and introduces a scalable method to enhance plan generation through a novel synthetic data generation method. Plan-and-Act consists of a Planner model which generates structured, high-level plans to achieve user goals, and an Executor model that translates these plans into environment-specific actions. To train the Planner effectively, we introduce a synthetic data generation method that annotates ground-truth trajectories with feasible plans, augmented with diverse and extensive examples to enhance generalization. We evaluate Plan-and-Act using web navigation as a representative long-horizon planning environment, demonstrating a state-of-the-art 57.58% success rate on the WebArena-Lite benchmark as well as a text-only state-of-the-art 81.36% success rate on WebVoyager.

Key facts. Cited by 195 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 48 of its 89 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

48 of 89 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration28 Aug
  2. 2024Tree Search for Language Model Agents1 Jul
  3. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models18 Sep
  4. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models26 May

Other references · 44

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  5. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  6. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  7. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  8. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
  9. 2023Textbooks Are All You Needcited by 569
  10. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  11. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  12. 2024WebVoyager: Building an End-to-End Web Agent with Large Multimodal Modelscited by 438
32 more
  1. 2023AppAgent: Multimodal Agents as Smartphone Userscited by 415
  2. 2024Agent Workflow Memorycited by 383
  3. 2023Language Models can Solve Computer Taskscited by 372
  4. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 353
  5. 2023Android in the Wild: A Large-Scale Dataset for Android Device Controlcited by 319
  6. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 256
  7. 2024DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learningcited by 214
  8. 2023An LLM Compiler for Parallel Function Callingcited by 179
  9. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 177
  10. 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
  11. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 160
  12. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agentscited by 154
  13. 2024Autonomous Evaluation and Refinement of Digital Agentscited by 137
  14. 2024AutoWebGLM: A Large Language Model-based Web Navigating Agentcited by 130
  15. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigationcited by 126
  16. 2024AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agentscited by 114
  17. 2024VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agentscited by 103
  18. 2024Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systemscited by 81
  19. 2024Beyond Browsing: API-Based Web Agentscited by 78
  20. 2024LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancementcited by 70
  21. 2024TinyAgent: Function Calling at the Edgecited by 58
  22. 2024Large Language Models Can Self-Improve At Web Agent Taskscited by 55
  23. 2024OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimizationcited by 46
  24. 2024Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scalecited by 43
  25. 2024A Survey on Data Synthesis and Augmentation for Large Language Modelscited by 41
  26. 2023Hierarchical Prompting Assists Large Language Model on Web Navigationcited by 36
  27. 2024LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environmentscited by 32
  28. 2023Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Webcited by 24
  29. 2024WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agentscited by 22
  30. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  31. 2024Geometric-Averaged Preference Optimization for Soft Preference Labelscited by 18
  32. 2024TinyClick: Single-Turn Agent for Empowering GUI Automationcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 63; 2026: 132.

195 papers.

Sort:

By area:

  1. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
  2. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 122
  3. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 116
  4. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 100
  5. 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
  6. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 75
  7. 2025Deep Research: A Survey of Autonomous Research Agentscited by 66
  8. 2025Embodied AI Agents: Modeling the Worldcited by 61
  9. 2025OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflowscited by 57
  10. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  11. 2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directionscited by 48
  12. 2026Code as Agent Harnesscited by 47
38 more
  1. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 45
  2. 2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interactioncited by 34
  3. 2025Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understandingcited by 29
  4. 2025SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graphcited by 28
  5. 2025LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Taskscited by 26
  6. 2026SkillGrad: Optimizing Agent Skills Like Gradient Descentcited by 26
  7. 2026The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Breakcited by 25
  8. 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answeringcited by 23
  9. 2026Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agentscited by 23
  10. 2025WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesiscited by 21
  11. 2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agentscited by 20
  12. 2025COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Contextcited by 20
  13. 2025Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoningcited by 19
  14. 2026From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systemscited by 19
  15. 2025SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agentscited by 17
  16. 2026Current Agents Fail to Leverage World Model as Tool for Foresightcited by 17
  17. 2026EvoRoute: Experience-Driven Self-Routing LLM Agent Systemscited by 16
  18. 2026AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robotscited by 16
  19. 2026Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agentscited by 16
  20. 2026JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolutioncited by 16
  21. 2026AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operationcited by 15
  22. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systemscited by 14
  23. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 14
  24. 2026When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigationcited by 14
  25. 2025Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Factscited by 13
  26. 2025AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecastingcited by 12
  27. 2026Evaluating Memory Structure in LLM Agentscited by 12
  28. 2025PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learningcited by 11
  29. 2026PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystemscited by 11
  30. 2025HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidancecited by 10
  31. 2025Generalizability of Large Language Model-Based Agents: A Comprehensive Surveycited by 10
  32. 2025Verification-Aware Planning for Multi-Agent Systemscited by 10
  33. 2025Routine: A Structural Planning Framework for LLM Agent System in Enterprisecited by 9
  34. 2026Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agentscited by 9
  35. 2026FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editingcited by 9
  36. 2026HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agentscited by 9
  37. 2026Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspectivecited by 9
  38. 2025What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignmentcited by 8

50 most cited of 195 All 195 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
  2. 2025Large Language Models for Planning: A Comprehensive and Systematic Survey
  3. 2024Query-Efficient Planning with Language Models
  4. 2025Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents
  5. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)
  6. 2025Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
  7. 2026PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models
  8. 2025Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution