mlsanityData to 14 Oct 2026

Mitigating Context Interference for Reliable and Efficient Search Agents

arXiv 2608.10743 ↗First posted 11 Aug 2026cs.CLcited by 1

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

Abstract (arXiv)

Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts of multi-turn search agents are lengthy and complex. For example, the retrieved set of documents in each turn would inevitably introduce irrelevant information that distracts LLMs, referring to textitcontext interference, potentially hindering the reliability and efficiency of search agents. Therefore, we conduct a systematic study on context interference in multi-turn search agents, focusing on investigating i) which parts of the context of search agents will contribute to the context interference, ii) how to refine the contexts of search agents to mitigate the interference, and iii) can incorporating context refinement into search agent training yield further improvements. We reveal that interference primarily arises from the latest retrieved documents. Based on the explored findings, we then introduce a distill-based context refiner to dynamically mitigate context interference for multi-turn search agents. Finally, we validate that incorporating context refinement into RL training pipelines of search agents can significantly enhance both reliability and efficiency. This study highlights the importance of mitigating context interference of search agents, inspiring a novel paradigm of ``refine context and then generate'' for AI agents.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 55 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

28 of 55 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training1 Aug
  2. 2025Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent12 May

Other references · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  10. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  11. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  12. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
14 more
  1. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  3. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  5. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  6. 2023Large Language Models in Finance: A Surveycited by 226
  7. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  8. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  9. 2025Benchmarking Prompt Sensitivity in Large Language Modelscited by 38
  10. 2025Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Modelscited by 23
  11. 2026Verified Critical Step Optimization for LLM Agentscited by 14
  12. 2024Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Informationcited by 8
  13. 2025Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Codecited by 5
  14. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Reading Too Much into Context: Passive Exposure Can Steer LLM Decisionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
  2. 2025Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
  3. 2026From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search
  4. 2026Entropic Context Shaping: Information-Theoretic Filtering for Context-Aware LLM Agents
  5. 2026The Context Gathering Decision Process: A POMDP Framework for Agentic Search
  6. 2026Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents
  7. 2025Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
  8. 2026SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task