Mitigating Context Interference for Reliable and Efficient Search Agents
- URL: http://arxiv.org/abs/2608.10743v1
- Date: Tue, 11 Aug 2026 10:00:42 GMT
- Title: Mitigating Context Interference for Reliable and Efficient Search Agents
- Abstract summary: This study investigates context interference in multi-turn search agents.<n>We introduce a distill-based context refiner to dynamically mitigate context interference for multi-turn search agents.<n>We validate that incorporating context refinement into RL training pipelines of search agents can significantly enhance both reliability and efficiency.
- Score: 67.82705889007238
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: 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 \textit{context 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.
Related papers
- SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration [77.28003194268977]
SearchOS is a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state.<n>Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents.<n>SearchOS leads all metrics among the evaluated single- and multi-agent baselines.
arXiv Detail & Related papers (2026-07-16T17:51:23Z) - Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging [14.434955701466597]
MultiSearch is an RL-based framework that addresses limitations through multi-query retrieval and explicit merging of retrieved information.<n>At each reasoning step, MultiSearch generates queries from multiple perspectives and retrieves external information in parallel, expanding the scope of relevant information.<n>Then, the agent consolidates and refines retrieved information at the merging process, improving the SNR and ensuring more accurate reasoning.
arXiv Detail & Related papers (2026-05-13T13:46:35Z) - AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning [52.305422887002656]
We propose a reinforcement learning framework that evaluates each search step via self-generated intermediate answers.<n>By a self-answering mechanism, AutoSearch identifies the minimal sufficient search depth and promotes efficient search.<n>Experiments show that AutoSearch achieves a superior accuracy-efficiency trade-off, alleviating over-searching while preserving search quality.
arXiv Detail & Related papers (2026-04-19T09:05:48Z) - Learning to Retrieve from Agent Trajectories [72.8923565916533]
We argue that retrieval models for agentic search should be trained directly from agent interaction data.<n>We introduce learning to retrieve from agent trajectories as a new training paradigm, where supervision is derived from multi-step agent interactions.<n>Our results highlight agent trajectories as a practical and scalable supervision source, pointing to a promising direction for retrieval in the era of agentic search.
arXiv Detail & Related papers (2026-03-30T17:59:02Z) - SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent [39.43590030917357]
SIGHT is a framework that enhances search-based reasoning through Self-Evidence Support and Information-Gain Driven Diverse Branching.<n>SIGHT distills search results into high-fidelity evidence via SES and calculates an Information Gain score to pinpoint pivotal states.<n> Experiments on single-hop and multi-hop QA benchmarks demonstrate that SIGHT significantly outperforms existing approaches.
arXiv Detail & Related papers (2026-02-12T04:16:55Z) - Over-Searching in Search-Augmented Large Language Models [22.821710825732563]
Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval.<n>Over-searching leads to computational inefficiency and hallucinations by incorporating irrelevant context.<n>Our finding shows: (i) search generally improves answer accuracy on answerable queries but harms abstention on unanswerable ones; (ii) over-searching is more pronounced in complex reasoning models and deep research systems; and (iii) the composition of retrieved evidence is crucial, as the presence of negative evidence improves abstention.
arXiv Detail & Related papers (2026-01-09T03:24:46Z) - Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search [56.78490647843876]
Agentic search has emerged as a promising paradigm for complex information seeking by enabling Large Language Models (LLMs) to interleave reasoning with tool use.<n>We propose bfM-ASK, a framework that explicitly decouples agentic search into two complementary roles: Search Behavior Agents, which plan and execute search actions, and Knowledge Management Agents, which aggregate, filter, and maintain a compact internal context.
arXiv Detail & Related papers (2026-01-08T08:13:27Z) - RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection [55.125987985864896]
We present a systematic analysis that quantifies how environmental complexity induces fragile search behaviors.<n>We propose a simple yet effective approach to instantiate a search agent, RE-Searcher.<n>This combination of goal-oriented planning and self-reflection enables RE-Searcher to resist spurious cues in complex search environments.
arXiv Detail & Related papers (2025-09-30T10:25:27Z)
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.