IE as Cache: Information Extraction Enhanced Agentic Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915940479795200 |
|---|---|
| author | Lv, Hang Liang, Sheng Gu, Hongchao Guo, Wei Lian, Defu Liu, Yong Wang, Hao Chen, Enhong |
| author_facet | Lv, Hang Liang, Sheng Gu, Hongchao Guo, Wei Lian, Defu Liu, Yong Wang, Hao Chen, Enhong |
| contents | Information Extraction aims to distill structured, decision-relevant information from unstructured text, serving as a foundation for downstream understanding and reasoning. However, it is traditionally treated merely as a terminal objective: once extracted, the resulting structure is often consumed in isolation rather than maintained and reused during multi-step inference. Moving beyond this, we propose \textit{IE-as-Cache}, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning. Drawing inspiration from hierarchical computer memory, our approach combines query-driven extraction with cache-aware reasoning to dynamically maintain compact intermediate information and filter noise. Experiments on challenging benchmarks across diverse LLMs demonstrate significant improvements in reasoning accuracy, indicating that IE can be effectively repurposed as a reusable cognitive resource and offering a promising direction for future research on downstream uses of IE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14930 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IE as Cache: Information Extraction Enhanced Agentic Reasoning Lv, Hang Liang, Sheng Gu, Hongchao Guo, Wei Lian, Defu Liu, Yong Wang, Hao Chen, Enhong Computation and Language Information Extraction aims to distill structured, decision-relevant information from unstructured text, serving as a foundation for downstream understanding and reasoning. However, it is traditionally treated merely as a terminal objective: once extracted, the resulting structure is often consumed in isolation rather than maintained and reused during multi-step inference. Moving beyond this, we propose \textit{IE-as-Cache}, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning. Drawing inspiration from hierarchical computer memory, our approach combines query-driven extraction with cache-aware reasoning to dynamically maintain compact intermediate information and filter noise. Experiments on challenging benchmarks across diverse LLMs demonstrate significant improvements in reasoning accuracy, indicating that IE can be effectively repurposed as a reusable cognitive resource and offering a promising direction for future research on downstream uses of IE. |
| title | IE as Cache: Information Extraction Enhanced Agentic Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.14930 |