AutoContext: Instance-Level Context Learning for LLM Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915725133742080 |
|---|---|
| author | Cai, Kuntai Liu, Juncheng Yang, Xianglin Niu, Zhaojie Xiao, Xiaokui Chen, Xing |
| author_facet | Cai, Kuntai Liu, Juncheng Yang, Xianglin Niu, Zhaojie Xiao, Xiaokui Chen, Xing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02369 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AutoContext: Instance-Level Context Learning for LLM Agents Cai, Kuntai Liu, Juncheng Yang, Xianglin Niu, Zhaojie Xiao, Xiaokui Chen, Xing Computation and Language Artificial Intelligence 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. |
| title | AutoContext: Instance-Level Context Learning for LLM Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.02369 |