aiqbench analysis
CorpusMap introduces an offline navigation layer that organizes document collections around recurring entities, enabling AI agents to traverse a shared graph for more efficient evidence discovery. By pre-resolving entity relationships, this approach reduces redundant token consumption during inference and improves answer quality across multiple models compared to flat corpus search methods. This advancement directly addresses the scalability challenges of agentic search in large, unstructured document environments.
Follow the Entities: A Corpus Map for Agentic Search
arXiv:2609.37226v1 Announce Type: new Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the agent must rediscover these relationships for every query, often missing complementary evidence while simultaneously consuming substantial additional tokens. To address this, we introduce CorpusMap, a navigation layer that organizes the corpus around its recurring entities, which are identifiable from the documents themselves and can link a single document to many others across sources. Specifically, CorpusMap represents each recurring entity as an Entity Page that aggregates information about it and links to every document that refers to it, forming a graph between entities and documents that the agent can traverse to gather otherwise disconnected evidence. Moreover, since CorpusMap is constructed offline by resolving mentions of the same entity across documents, its links are shared across queries rather than rediscovered repeatedly at inference time. Using 7 different models with 3 benchmark datasets, we show that CorpusMap improves both evidence discovery and answer quality over raw-corpus agentic search while using fewer tokens on average, and further outperforms 4 alternative navigation layers, suggesting that entities serve as effective anchors for navigating large document collections.
Abstract:Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the agent must rediscover these relationships for every query, often missing complementary evidence while simultaneously consuming substantial additional tokens. To address this, we introduce CorpusMap, a navigation layer that organizes the corpus around its recurring entities, which are identifiable from the documents themselves and can link a single document to many others across sources. Specifically, CorpusMap represents each recurring entity as an Entity Page that aggregates information about it and links to every document that refers to it, forming a graph between entities and documents that the agent can traverse to gather otherwise disconnected evidence. Moreover, since CorpusMap is constructed offline by resolving mentions of the same entity across documents, its links are shared across queries rather than rediscovered repeatedly at inference time. Using 7 different models with 3 benchmark datasets, we show that CorpusMap improves both evidence discovery and answer quality over raw-corpus agentic search while using fewer tokens on average, and further outperforms 4 alternative navigation layers, suggesting that entities serve as effective anchors for navigating large document collections.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
arXiv:2609.37226 [cs.CL]
(or arXiv:2609.37226v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.37226 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 358 words
Related coverage
Scaling Karpathy’s LLM wiki: Why your knowledge base needs a graph
Neo4j · Aug 31, 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026
Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b
MarkTechPost · Jun 7, 2026
Implementing and Evaluating a Basic Per-Action Monitor for Safer Evals
METR · Sep 27, 2026