IE as Cache: Information Extraction Enhanced Agentic Reasoning

arXiv:2604.14930v1 Announce Type: new Abstract: 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 extit{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.

Related

• Reasoning Graphs: Deterministic Agent Accuracy through Evidence-Centric Chain-of-Thought Feedback
• Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning
• NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation
• SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval

Source: arXiv cs.CL | 2026-04-17