mlsanityData to 7 Oct 2026

DeepResearch-Slice: Bridging the Retrieval-Utilization Gap via Explicit Text Slicing

arXiv 2601.03261 ↗First posted 16 Dec 2025cs.CL cs.AIcited by 7

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due to context blindness in noisy environments. To bridge this gap, we propose DeepResearch-Slice, a simple yet effective neuro-symbolic framework. Unlike implicit attention, our approach predicts precise span indices to perform a deterministic hard filter before reasoning. Extensive evaluations across six benchmarks show substantial robustness gains. Applying our method to frozen backbones yields a 73 percent relative improvement, from 19.1 percent to 33.0 percent, effectively mitigating noise without requiring parameter updates to the reasoning model. These results highlight the need for explicit grounding mechanisms in open-ended research.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 28 references that are in the map. First posted on arXiv 16 Dec 2025.

Builds on

19 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Mind2Web: Towards a Generalist Agent for the Web9 Jun

Other references · 18

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  10. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  11. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  12. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
6 more
  1. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  2. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 350
  3. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  4. 2016Rationalizing Neural Predictionscited by 281
  5. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
  6. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Timecited by 10
  2. 2026How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1cited by 6
  3. 2026WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesiscited by 6
  4. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
  5. 2026Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstrativescited by 0
  6. 2026Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspectivecited by 0
  7. 2026DualStake: Dual-Path Confidence Calibration in Deep Research Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AgentIR: Reasoning-Aware Retrieval for Deep Research Agents
  2. 2026Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
  3. 2026DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search
  4. 2026Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval
  5. 2025Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs
  6. 2025DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking
  7. 2026DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
  8. 2026Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking