arXiv AI
AtlasNav: Mitigating Evidence Blindness with Persistent Corpus Navigation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 26
Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav
The paper introduces AtlasNav, a persistent multi‑view corpus‑navigation framework that organizes a corpus into a Corpus Atlas, enabling large‑language‑model agents to navigate efficiently under finite interaction budgets. AtlasNav reduces online inference cost by 30.21% and achieves 92.05% strict accuracy on BrowseComp‑Plus, while earlier and more rapidly realizing required evidence compared to dynamic‑workspace methods. The approach also transfers well to other corpora such as PhantomWiki and heterogeneous enterprise knowledge bases, demonstrating that effective agentic search relies on both accessible evidence and a reusable corpus representation.
arXiv AI
4d ago
Follow the Entities: A Corpus Map for Agentic Search
arXiv:2609.37226v1 Announce Type: cross Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as...
arXiv AI
Jun 16
Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
arXiv:2606. 14885v1 Announce Type: new Abstract: Agentic search over large corpora relies on retriever-mediated interfaces (e.
arXiv AI
Aug 10
DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding
arXiv:2608. 07067v1 Announce Type: new Abstract: Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory.
arXiv Machine Learning
Sep 11
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
The paper introduces REVA, a method for compressing retrieval-augmented generation (RAG) prompts by aggregating historical query–document–model interactions into reusable evidence views. REVA mines attention traces from the target generator, maps token-level attention to readable words, aggregates importance across repeated document accesses, and produces budget‑specific plain‑text views that maintain document order and the standard RAG interface. Experiments on four benchmarks with modern LLMs show that REVA improves generation quality by 1.0–5.8 points over existing compressors while reducing compression overhead by 5.3 to 15.6 times and adding less than 40 ms of latency.
arXiv AI
Aug 11
DocAtlas: Long-Document Understanding as Mutable-State Interaction
arXiv:2608. 07527v1 Announce Type: cross Abstract: Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts.