让大模型智能体学会记住环境细节，一次探索永久使用。
AutoContext: Instance-Level Context Learning for LLM Agents
- 通过一次性系统性探索构建可复用的知识图谱
- 在TextWorld上任务成功率从37%提升至95%
- 适合需要长期记忆的复杂任务场景
当前大模型智能体普遍缺乏实例级上下文，即环境结构、系统配置和本地机制等具体事实。因此，现有方法不得不将探索与任务执行耦合，导致重复交互和决策脆弱。为解决此问题，我们提出AutoContext，该方法将探索与任务求解解耦。AutoContext对每个环境实例进行一次性的系统性探索，构建可复用的知识图谱。该结构化上下文使现成智能体能直接获取必要信息，避免重复探索。在TextWorld、ALFWorld、Crafter和InterCode-Bash上的实验表明，性能显著提升：例如，ReAct智能体在TextWorld上的成功率从37%提升至95%，凸显了结构化实例上下文在高效智能体系统中的关键作用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。