mlsanityData to 7 Oct 2026

AutoContext: Instance-Level Context Learning for LLM Agents

arXiv 2510.02369 ↗First posted 29 Sep 2025cs.CL cs.AIcited by 1

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

Abstract (arXiv)

Current LLM agents typically lack instance-level context, which comprises concrete facts such as environment structure, system configurations, and local mechanics. Consequently, existing methods are forced to intertwine exploration with task execution. This coupling leads to redundant interactions and fragile decision-making, as agents must repeatedly rediscover the same information for every new task. To address this, we introduce AutoContext, a method that decouples exploration from task solving. AutoContext performs a systematic, one-off exploration to construct a reusable knowledge graph for each environment instance. This structured context allows off-the-shelf agents to access necessary facts directly, eliminating redundant exploration. Experiments across TextWorld, ALFWorld, Crafter, and InterCode-Bash demonstrate substantial gains: for example, the success rate of a ReAct agent on TextWorld improves from 37% to 95%, highlighting the critical role of structured instance context in efficient agentic systems.

Key facts. Cited by 1 paper 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 45 of its 69 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

45 of 69 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025Fact-Augmented Lookahead Planning for LLM Agents10 Jun
  2. 2025SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement4 Apr
  3. 2024Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement17 Jun
  4. 2024AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning25 May
  5. 2024Agent Planning with World Knowledge Model23 May
  6. 2024WESE: Weak Exploration to Strong Exploitation for LLM Agents11 Apr
  7. 2024ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy21 Mar
  8. 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents13 Mar
  9. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents5 Mar
  10. 2024Bootstrapping Cognitive Agents with a Large Language Model25 Feb
  11. 2024Empowering Large Language Model Agents through Action Learning24 Feb
  12. 2024AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback2 Feb
2 more
  1. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug
  2. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May

Other references · 31

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  7. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  8. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  9. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  10. 2020Mastering Atari with Discrete World Modelscited by 990
  11. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  12. 2025Seed1.5-VL Technical Reportcited by 367
19 more
  1. 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
  2. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  3. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  4. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  5. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 193
  6. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 185
  7. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  8. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  9. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigationcited by 116
  10. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  11. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  12. 2020Graph Constrained Reinforcement Learning for Natural Language Action Spacescited by 80
  13. 2024RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agentscited by 80
  14. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 66
  15. 2024Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Modelscited by 32
  16. 2025AgentRM: Enhancing Agent Generalization with Reward Modelingcited by 25
  17. 2025Scaling Autonomous Agents via Automatic Reward Modeling And Planningcited by 19
  18. 2024Language Guided Exploration for RL Agents in Text Environmentscited by 9
  19. 2024STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Modelscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agentscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses
  2. 2026Unified Context Evolution for LLM Agents
  3. 2026Learning Agent-Compatible Context Management for Long-Horizon Tasks
  4. 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
  5. 2026Look Before You Leap: Autonomous Exploration for LLM Agents
  6. 2026LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
  7. 2026Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning
  8. 2026Multi-Agent LLMs Fail to Explore Each Other