ACARE: Agent-Context-Aware Reranker for Iterative Search

Researchers submitted ACARe (Agent-Context-Aware Reranker), a compact 4B LLM trained to rerank documents using the agent's broader task and reasoning context rather than the sub-query alone, to arXiv on 26 October 2026. Across multiple benchmarks and agent families, ACARe improved retrieval quality over its base reranker while reducing search effort, and in answer generation it improved accuracy and cut searches versus no reranking while matching or exceeding the base reranker's mean accuracy with more precise evidence. The work also narrowed the retrieval-quality gap between smaller and larger agents, and the model, training data and code are slated for release.

Computer Science Information Retrieval Submitted on 26 Oct 2026 Title:ACARE: Agent-Context-Aware Reranker for Iterative Search View PDF http://arxiv.org/pdf/2610.35840v1 HTML experimental https://arxiv.org/html/2610.35840v1 Abstract:In agentic search, a document can match an agent-generated sub-query without helping answer the user's original question. Conventional rerankers score documents against the sub-query alone, overlooking the broader task and the agent's reasoning. We introduce the Agent-Context-Aware Reranker ACARe , a compact 4B LLM trained to rerank documents using this context when available. Across multiple benchmarks and agent families, ACARe improves retrieval quality over its base reranker while reducing search effort. These benefits extend to answer generation: ACARe improves accuracy and reduces searches over no reranking, while matching or exceeding the base reranker's mean accuracy with more precise evidence. It also helps smaller agents narrow the retrieval-quality gap to larger agents, showing how better retrieval tools can make smaller agents more effective. The model, training data, and code will be released soon. Submission history From: Sahel Sharifymoghaddam view email http://arxiv.org/show-email/63a415f3/2610.35840 v1 Mon, 26 Oct 2026 17:53:30 UTC 176 KB Additional Features References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .