Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

• URL: http://arxiv.org/abs/2605.05242v1
• Date: Sun, 03 May 2026 19:13:11 GMT
• Title: Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
• Abstract summary: We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
• Score: 127.64173950476702
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical constraints, sparse clue conjunctions, local context checks, and multi-step hypothesis refinement are difficult to implement by calling a conventional off-the-shelf retriever, and evidence filtered out early cannot be recovered by stronger downstream reasoning. Agentic tasks further exacerbate this limitation because they require agents to orchestrate multiple steps, including discovering intermediate entities, combining weak clues, and revising the plan after observing partial evidence. To tackle the limitation, we study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools (e.g., grep, file reads, shell commands, lightweight scripts), without any embedding model, vector index, or retrieval API. This approach requires no offline indexing and adapts naturally to evolving local corpora. Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines on several BRIGHT and BEIR datasets, and attains strong accuracy on BrowseComp-Plus and multi-hop QA without relying on any conventional semantic retriever. Our results indicate that as language agents become stronger, retrieval quality depends not only on reasoning ability but also on the resolution of the interface through which the model interacts with the corpus, with which DCI opens a broader interface-design space for agentic search.

Related papers

• A New Role for Relevance: Guiding Corpus Interaction in Agentic Search [45.65771530564621]
  Relevance is a query-dependent estimate of whether a document or excerpt contains useful evidence.<n>We introduce the Relevance-Aware RipGrep Search Agent (RARG), which turns relevance into an execution prior to interaction.
  arXiv  Detail & Related papers  (2026-07-27T09:56:52Z)
• Towards Retrieving Interaction Spaces for Agentic Search [62.666902610940525]
  Recent direct corpus (DCI) work shows that agents can interact with the raw corpus through shell tools such as 5.4 interaction and file reads.<n>We argue that the role of retrieval for agentic search is not just to select documents that fit in the LLM context window, but to construct an interaction space.
  arXiv  Detail & Related papers  (2026-06-05T03:47:40Z)
• GrepSeek: Training Search Agents for Direct Corpus Interaction [66.69568141699311]
  GrepSeek is an optimized direct corpus interaction (DCI) search agent that trains a compact search agent to find, filter, and compose evidence from large text corpora.<n>To make DCI practical at scale, we further use a semantics-preserving sharded-parallel execution engine that accelerates shell-based retrieval by up to $7.6times$ while preserving byte-exact equivalence with sequential execution of the shell command.
  arXiv  Detail & Related papers  (2026-05-28T03:37:33Z)
• Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval [25.731213365755234]
  We introduce textitSuperIntelligent Retrieval Agent (SIRA)<n>SIRA can compress multi-round exploratory search into a single corpus-discriminative retrieval action.<n>It can exceed substantially more expensive multi-round search while remaining interpretable, training-free, and efficient.
  arXiv  Detail & Related papers  (2026-05-07T17:54:29Z)
• OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries [20.960193343595492]
  OBLIQ-Bench is a suite of five oblique search problems over real long-tail corpora.<n>OBLIQ-Bench exposes an overlooked asymmetry between retrieval and verification.<n>We hope that OBLIQ-Bench will drive research into retrieval architectures that efficiently capture latent patterns and implicit signals in large corpora.
  arXiv  Detail & Related papers  (2026-05-07T13:22:49Z)
• Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search [45.34874989015716]
  Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries.<n>Recent pose-aware methods face a fundamental Pose-Semantic Gap: semantically different actions can share similar skeletal geometries.<n>We propose the Structure-Semantic Decoupled Cascade (SSDC) framework, which decouples retrieval into two stages.
  arXiv  Detail & Related papers  (2026-04-25T12:53:15Z)
• Rethinking Deep Research from the Perspective of Web Content Distribution Matching [86.90255285277256]
  We propose WeDas, a Web Content Distribution Aware framework that incorporates search-space structural characteristics into the agent's observation space.<n>We introduce a few-shot probing mechanism that iteratively estimates the Query-Result Alignment Score.<n>As a plug-and-play module, WeDas consistently improves sub-goal completion and accuracy across four benchmarks.
  arXiv  Detail & Related papers  (2026-03-07T14:51:17Z)
• GrepRAG: An Empirical Study and Optimization of Grep-Like Retrieval for Code Completion [32.17127975368661]
  Repository-level code completion remains challenging for large language models.<n>We investigate lightweight, index-free, intent-aware lexical retrieval.<n>We introduce Naive GrepRAG, a baseline framework in which LLMs autonomously generate ripweighted commands to retrieve relevant context.
  arXiv  Detail & Related papers  (2026-01-30T18:22:15Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection [7.030364980618468]
  We propose a novel plug-and-play HOI detection framework that incorporates semantic priors and guided feature learning.<n>Our method achieves state-of-the-art performance and strong generalizations on HICO-Det and V-COCO benchmarks.
  arXiv  Detail & Related papers  (2025-08-12T03:11:16Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)

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.