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.
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.
Related stories
Hugging Face Trending Papers
Aug 17
LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents
LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmented approaches pre-materialize evidence via fixed chunking, embeddings, or persistent indexes: effective for lookup, yet costly, stale-prone, and committed to a granularity before the query is known.
arXiv AI
Aug 18
LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents
arXiv:2608. 16185v1 Announce Type: cross Abstract: LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent.
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.
arXiv AI
Jun 30
HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning
arXiv:2606. 28349v1 Announce Type: cross Abstract: Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories.
Hugging Face Trending Papers
Aug 17
Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate
Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time. Put plainly, instead of re-deriving what a corpus means on every question, the work is done once when a document arrives and is thereafter merely consulted -- a compiler, not an interpreter, of meaning.
arXiv AI
Jun 30
CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval
arXiv:2606. 28365v1 Announce Type: cross Abstract: RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.
arXiv AI
Aug 18
Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate
arXiv:2608. 16621v1 Announce Type: new Abstract: Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time.
arXiv AI
Jun 8
Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval
arXiv:2605. 06647v2 Announce Type: replace-cross Abstract: Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet most treat retrieval as a black box: they issue exploratory queries, inspect snippets, and reformulate until evidence emerges.
arXiv AI
Jul 17
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
arXiv:2607. 15257v1 Announce Type: new Abstract: Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents.
arXiv AI
Aug 20
ICICLE: Expanding Retrieval with In-Context Documents
ICICLE is an in‑context indexing framework that expands generative retrieval by supplying newly added documents as inference‑time evidence. It generates document identifiers using both parametric memory and context‑provided document‑docid pairs, employing a [COPY] routing mechanism, preference‑based calibration, and large‑context adaptation to separate context‑grounded retrieval from parametric retrieval. Experiments on MS MARCO and NQ320K demonstrate that ICICLE improves retrieval of new documents while retaining performance on previously indexed documents without retraining the model.
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.