Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents

• URL: http://arxiv.org/abs/2608.02097v1
• Date: Mon, 03 Aug 2026 11:58:21 GMT
• Title: Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents
• Abstract summary: We propose textbfFetch-then-Explore for search agents.<n>It separates page selection from evidence extraction and keeps what it selects.<n>It leads BrowseComp accuracy at every backbone and generally matches or exceeds the baselines on WideSearch.
• Score: 60.97609995940902
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Search agents now answer questions that take dozens of searches to settle, yet how such an agent reads a page has drawn far less attention than how it finds one. Nearly all of them use one of two document interfaces, and both tie a page to the moment it is opened. \emph{Visit-and-read} injects a reading of the page into the message history at fetch time, fixing that reading before the agent knows which fact it will need. Stateful \emph{browsing} instead extracts on demand from the page in hand, but holds one page at a time and releases it as soon as the agent opens another. Either way, a page that turns out to matter many turns later has to be fetched and rendered into context all over again. We propose \textbf{Fetch-then-Explore}, which separates page selection from evidence extraction and keeps what it selects: pages are recorded in a per-question workspace on the filesystem rather than the context window or a transient session, and evidence is pulled from them on demand later. Selection becomes almost free, extraction can wait until the agent knows what to look for and be repeated as its hypothesis sharpens, and pages are not released when the agent moves on, so evidence accumulates across the trajectory. In a unified ReAct harness with fixed search, we compare Fetch-then-Explore against snippet-only, visit-and-read, and browsing baselines on two open-web benchmarks, BrowseComp and WideSearch, across three agent backbones. It leads BrowseComp accuracy at every backbone and generally matches or exceeds the baselines on WideSearch, and a behavioral analysis traces the gains to the workspace's defining move: returning to a page after leaving it, which it does far more than any transient interface, so evidence missed on a first pass can still be recovered later.

Related papers

• Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation [50.92223196290564]
  We propose a unified agent loop for explicit evidence selection and consolidation.<n>During exploration, SCoRE retains only query-relevant observations and their source pointers in a maintained textual ledger.<n>At termination, it reloads the referenced original images and consolidates the visual evidence for answering, arranging it into a logical sequence.
  arXiv  Detail & Related papers  (2026-09-14T16:11:35Z)
• VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval [65.89247522243959]
  VisDocAgentBench is a closed-corpus benchmark comparing static and agentic retrieval under a ranked-output contract.<n>It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures.<n>A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query--target matching when relevance depends on corpus context.
  arXiv  Detail & Related papers  (2026-08-18T15:23:06Z)
• Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Research Agents [50.35041517085015]
  Existing deep-research agents use a Search--Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata.<n>We introduce textscSieve, a search--inspect-fetch strategy driven by a Boolean Query Language (BQL)<n>It searches webpage fields to filter candidates, uses an interchangeable ranker to order them, presents structure-rich result cards for inspection, and fetches only selected sections.
  arXiv  Detail & Related papers  (2026-08-03T18:01:05Z)
• Is Progressive Disclosure All You Need for Long-Context Agents? [6.214989743502112]
  Agentic AI suggests a broader option, giving the agent the document path and letting it decide how and what to read.<n>Agent Skills, a standard for packaging expertise into an agent loads on demand, supply a ready mechanism: progressive disclosure.<n>We run the first controlled study of the pattern, comparing raw-document navigation and several designs of Agent Skills packs against a classical hybrid retriever.
  arXiv  Detail & Related papers  (2026-07-20T06:35:32Z)
• DRNOISE: Benchmarking Deep Research Agents in Misleading Evidence Environments [51.049999642138]
  We introduce DRNOISE, a 100-task benchmark for answer recovery under misleading evidence.<n>Each task has a unique gold answer supported by two corroborating indirect record chains; the paired noisy condition adds one plausible document that states a conflicting answer directly.<n>Across agents with strong clean-task performance, this single intervention causes 66-88 percentage-point accuracy drops.
  arXiv  Detail & Related papers  (2026-07-19T15:20:40Z)
• Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search [3.976291254896486]
  Retrieval systems are trained and evaluated on a static idea of usefulness.<n>It breaks when a language model works as a search agent, issuing several queries and reasoning across turns.<n>We replay 1000 development questions and, for every document the agent read, delete it and re-run the rest of the trajectory from that point.
  arXiv  Detail & Related papers  (2026-07-16T17:48:29Z)
• PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents [0.9134244356393664]
  LLM agents operate over a context window that fills from several directions simultaneously.<n>The prevailing mechanism is recency truncation, sometimes paired with periodic summarization.<n>Retrieval augmented generation fetches external documents into the prompt but does not arbitrate the agent's emphalready-present pooled context.
  arXiv  Detail & Related papers  (2026-06-18T10:22:57Z)
• EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval [22.402302777838724]
  We propose EviProp, a retrieval method that recovers evidence pages via seeded relevance diffusion.<n>EviProp models each document as a multimodal Chunk-Page graph with hierarchical, sequential, and similarity links.<n> Experiments on MMLongBench-Doc and LongDocURL show consistent gains in evidence-page retrieval over independent visual retrieval and text-visual fusion baselines.
  arXiv  Detail & Related papers  (2026-06-08T03:25:20Z)
• Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation [74.0621258662676]
  We propose Ptah, a multi-agent harness for interleaved report generation.<n>Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages.<n>A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow.
  arXiv  Detail & Related papers  (2026-05-28T12:40:34Z)
• Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA [71.42483000929614]
  Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.<n>We propose Doc-$V*$, an textbfOCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
  arXiv  Detail & Related papers  (2026-04-15T11:12:27Z)
• SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement [17.272061289197342]
  Document Visual Question Answering (DocVQA) is a practical yet challenging task.<n>Recent methods follow a similar Retrieval Augmented Generation (RAG) pipeline.<n>We introduce SimpleDoc, a lightweight yet powerful retrieval - augmented framework for DocVQA.
  arXiv  Detail & Related papers  (2025-06-16T22:15:58Z)
• DAPR: A Benchmark on Document-Aware Passage Retrieval [57.45793782107218]
  We propose and name this task emphDocument-Aware Passage Retrieval (DAPR) While analyzing the errors of the State-of-The-Art (SoTA) passage retrievers, we find the major errors (53.5%) are due to missing document context. Our created benchmark enables future research on developing and comparing retrieval systems for the new task.
  arXiv  Detail & Related papers  (2023-05-23T10:39:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.