mlsanityData to 7 Oct 2026

AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents

arXiv 2403.08978 ↗First posted 13 Mar 2024cs.CL cs.LGcited by 69

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

Abstract (arXiv)

Recent advances in large language models (LLMs) have empowered AI agents capable of performing various sequential decision-making tasks. However, effectively guiding LLMs to perform well in unfamiliar domains like web navigation, where they lack sufficient knowledge, has proven to be difficult with the demonstration-based in-context learning paradigm. In this paper, we introduce a novel framework, called AutoGuide, which addresses this limitation by automatically generating context-aware guidelines from offline experiences. Importantly, each context-aware guideline is expressed in concise natural language and follows a conditional structure, clearly describing the context where it is applicable. As a result, our guidelines facilitate the provision of relevant knowledge for the agent's current decision-making process, overcoming the limitations of the conventional demonstration-based learning paradigm. Our evaluation demonstrates that AutoGuide significantly outperforms competitive baselines in complex benchmark domains, including real-world web navigation.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 29 of its 37 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

29 of 37 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  3. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  4. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug
  5. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models26 May

Other references · 24

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  7. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  9. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  10. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  11. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  12. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
12 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  2. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  3. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  4. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  5. 2022PAL: Program-aided Language Modelscited by 635
  6. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 547
  7. 2023Language Models can Solve Computer Taskscited by 371
  8. 2023Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4Vcited by 291
  9. 2022TALM: Tool Augmented Language Modelscited by 197
  10. 2021Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learningcited by 45
  11. 2014Learning to Win by Reading Manuals in a Monte-Carlo Frameworkcited by 39
  12. 2022Few-shot Subgoal Planning with Language Modelscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 26; 2026: 39.

69 papers.

Sort:

By area:

  1. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  2. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learningcited by 162
  3. 2025Evaluation and Benchmarking of LLM Agents: A Surveycited by 145
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  5. 2024Beyond Browsing: API-Based Web Agentscited by 77
  6. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 64
  7. 2025Contextual Experience Replay for Self-Improvement of Language Agentscited by 46
  8. 2024ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Datacited by 39
  9. 2025MPO: Boosting LLM Agents with Meta Plan Optimizationcited by 36
  10. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
  11. 2024THREAD: Thinking Deeper with Recursive Spawningcited by 24
  12. 2025Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Taskscited by 17
38 more
  1. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  2. 2026SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scalecited by 15
  3. 2025Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answeringcited by 12
  4. 2026Experiential Reflective Learning for Self-Improving LLM Agentscited by 12
  5. 2025Formalizing Learning from Language Feedback with Provable Guaranteescited by 10
  6. 2025OpenApps: Simulating Environment Variations to Measure UI-Agent Reliabilitycited by 10
  7. 2026Dynamic Skill Lifecycle Management for Agentic Reinforcement Learningcited by 10
  8. 2025H2R: Hierarchical Hindsight Reflection for Multi-Task LLM Agentscited by 8
  9. 2026WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agentscited by 7
  10. 2025PG-Agent: An Agent Powered by Page Graphcited by 6
  11. 2025Reflection-Based Memory For Web navigation Agentscited by 5
  12. 2025Fine-tuning with RAG for Improving LLM Learning of New Skillscited by 5
  13. 2025JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptationcited by 5
  14. 2026Large Language Model Agents Are Not Always Faithful Self-Evolverscited by 5
  15. 2025EDGE: Efficient Data Selection for LLM Agents via Guideline Effectivenesscited by 4
  16. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 4
  17. 2026Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operationscited by 4
  18. 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnessescited by 4
  19. 2025On the Role of Feedback in Test-Time Scaling of Agentic AI Workflowscited by 3
  20. 2025Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scalecited by 3
  21. 2025Universal Retrieval for Multimodal Trajectory Modelingcited by 3
  22. 2026Mem-π: Adaptive Memory through Learning When and What to Generatecited by 3
  23. 2026FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewardscited by 3
  24. 2026SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolutioncited by 3
  25. 2025Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt Engineeringcited by 2
  26. 2026AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactionscited by 2
  27. 2024One STEP at a time: Language Agents are Stepwise Plannerscited by 1
  28. 2025D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agentscited by 1
  29. 2025AutoContext: Instance-Level Context Learning for LLM Agentscited by 1
  30. 2026WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agentscited by 1
  31. 2026View-oriented Conversation Compiler for Agent Trace Analysiscited by 1
  32. 2026Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Modelscited by 1
  33. 2026FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcastcited by 1
  34. 2026Progressive Agent Skill Generation via Reinforcement Learningcited by 1
  35. 2026Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Modelscited by 1
  36. 2026Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agentscited by 1
  37. 2025Prompt-aware classifier free guidance for diffusion modelscited by 0
  38. 2026PRISM: Learning Design Knowledge from Data for Stylistic Design Improvementcited by 0

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents
  2. 2024Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents
  3. 2025Leveraging In-Context Learning for Language Model Agents
  4. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
  5. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
  6. 2025Towards more Contextual Agents: An extractor-Generator Optimization Framework
  7. 2024AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning
  8. 2024AutoWebGLM: A Large Language Model-based Web Navigating Agent