CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search

• URL: http://arxiv.org/abs/2604.17555v2
• Date: Tue, 21 Apr 2026 18:00:25 GMT
• Title: CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
• Abstract summary: CoSearch is a framework that jointly trains a multi-step reasoning agent and a generative document ranking model.<n>Our results show that joint training of the reasoning agent and retrieval system is both feasible and strongly performant.
• Score: 51.911048955965136
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic search -- the task of training agents that iteratively reason, issue queries, and synthesize retrieved information to answer complex questions -- has achieved remarkable progress through reinforcement learning (RL). However, existing approaches such as Search-R1, treat the retrieval system as a fixed tool, optimizing only the reasoning agent while the retrieval component remains unchanged. A preliminary experiment reveals that the gap between an oracle and a fixed retrieval system reaches up to +26.8% relative F1 improvement across seven QA benchmarks, suggesting that the retrieval system is a key bottleneck in scaling agentic search performance. Motivated by this finding, we propose CoSearch, a framework that jointly trains a multi-step reasoning agent and a generative document ranking model via Group Relative Policy Optimization (GRPO). To enable effective GRPO training for the ranker -- whose inputs vary across reasoning trajectories -- we introduce a semantic grouping strategy that clusters sub-queries by token-level similarity, forming valid optimization groups without additional rollouts. We further design a composite reward combining ranking quality signals with trajectory-level outcome feedback, providing the ranker with both immediate and long-term learning signals. Experiments on seven single-hop and multi-hop QA benchmarks demonstrate consistent improvements over strong baselines, with ablation studies validating each design choice. Our results show that joint training of the reasoning agent and retrieval system is both feasible and strongly performant, pointing to a key ingredient for future search agents.

Related papers

• Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study [31.167867050243256]
  ThinkGR is a unified framework that interleaves chain-of-thought with docid generation, enabling iterative thinking and retrieval within a single generative process.<n> Experiments on four multi-hop retrieval benchmarks demonstrate that ThinkGR achieves state-of-the-art performance with an average improvement of +6.86%.
  arXiv  Detail & Related papers  (2026-05-21T11:48:35Z)
• MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning [74.07254720088926]
  We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering.<n>We propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO.<n>Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%.
  arXiv  Detail & Related papers  (2026-04-15T07:39:08Z)
• PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training [28.912613644535668]
  We present PRAISE, a framework for improving data efficiency and credit assignment in agentic search training.<n>Our method uses a single shared model for both search policy learning and prefix answer evaluation.<n>Experiments on multi-hop QA benchmarks show that PRAISE consistently improves performance over strong baselines.
  arXiv  Detail & Related papers  (2026-04-04T10:23:46Z)
• 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)
• APEX-Searcher: Augmenting LLMs' Search Capabilities through Agentic Planning and Execution [10.643859464982071]
  APEX-Searcher is a novel Agentic Planning and Execution framework to augment large language models (LLMs) search capabilities.<n>It first employs RL with decomposition-specific rewards to optimize strategic planning.<n>It then applies supervised fine-tuning on high-quality multi-hop trajectories to equip the model with robust iterative sub-task execution capabilities.
  arXiv  Detail & Related papers  (2026-03-14T09:17:12Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning [26.489185170468062]
  We propose a novel RL framework called Adaptive Complex Query Optimization (ACQO)<n>Our framework is designed to adaptively determine when and how to expand the search process.<n>ACQO achieves state-of-the-art performance on three complex query benchmarks, significantly outperforming established baselines.
  arXiv  Detail & Related papers  (2026-01-29T03:16:53Z)
• SmartSearch: Process Reward-Guided Query Refinement for Search Agents [63.46067892354375]
  Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems.<n>Existing works largely focus on optimizing the reasoning paradigms of search agents, yet the quality of intermediate search queries during reasoning remains overlooked.<n>We introduce SmartSearch, a framework built upon two key mechanisms to mitigate this issue.
  arXiv  Detail & Related papers  (2026-01-08T12:39:05Z)
• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents [19.31471304268234]
  We introduce DeSA (Decoupling Search-and-Answering), a simple two-stage training framework that explicitly separates search optimization from answer generation.<n>Across seven QA benchmarks, DeSA-trained agents consistently improve search behaviors, delivering substantially higher search recall and answer accuracy than outcome-only baselines.
  arXiv  Detail & Related papers  (2025-10-06T11:09:45Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)

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.