WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2602.04634v1
• Date: Wed, 04 Feb 2026 15:05:12 GMT
• Title: WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
• Authors: Zelai Xu, Zhexuan Xu, Ruize Zhang, Chunyang Zhu, Shi Yu, Weilin Liu, Quanlu Zhang, Wenbo Ding, Chao Yu, Yu Wang,
• Abstract summary: Existing multi-agent systems often rely on hand-crafted and turn-taking interactions that fail to parallelize work effectively.<n>We propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution.<n>Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B.
• Score: 15.087327596252932
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts from individual competence to organizational capability. In this work, we explore a complementary dimension of width scaling with multi-agent systems to address broad information seeking. Existing multi-agent systems often rely on hand-crafted workflows and turn-taking interactions that fail to parallelize work effectively. To bridge this gap, we propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution. By utilizing a shared LLM with isolated contexts and specialized tools, WideSeek-R1 jointly optimizes the lead agent and parallel subagents on a curated dataset of 20k broad information-seeking tasks. Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B. Furthermore, WideSeek-R1-4B exhibits consistent performance gains as the number of parallel subagents increases, highlighting the effectiveness of width scaling.

Related papers

• MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation [64.2621682259008]
  Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2)<n>We propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2) to integrate policy learning with multi-agent tree search.<n>We show that MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1 on challenging code generation benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T07:28:44Z)
• W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents [48.22725588392165]
  We propose a framework designed to investigate the behavior and performance of agents when scaling not only depth but also width via parallel tool calling.<n>We demonstrate that scaling width significantly improves performance on deep research benchmarks while reducing the number of turns required to obtain correct answers.<n>Our findings suggest that optimizing the trade-off between width and depth is a critical pathway toward high-efficiency deep research agents.
  arXiv  Detail & Related papers  (2026-02-07T04:49:53Z)
• WideSeek: Advancing Wide Research via Multi-Agent Scaling [29.02742625120584]
  Wide Research is a paradigm essential for synthesizing and synthesizing comprehensive information under complex constraints in parallel.<n>We take a deep dive into Wide Research from two perspectives: Data Pipeline and Agent Optimization.<n>First, we produce WideSeekBench, a benchmark constructed via a rigorous multi-phase data pipeline to ensure diversity across the target information volume.<n>Second, we introduce WideSeek, a dynamic hierarchical multi-agent architecture that can autonomously fork parallel sub-agents based on task requirements.
  arXiv  Detail & Related papers  (2026-02-02T18:32:48Z)
• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling [48.18456242206804]
  We present a systematic analysis of how to leverage multimodal signals across both stages of lifelong modeling framework.<n>We propose MUSE, a simple yet effective multimodal search-based framework.<n>MUSE has been deployed in Taobao display advertising system, enabling 100K-length user behavior sequence modeling.
  arXiv  Detail & Related papers  (2025-12-08T06:55:13Z)
• Training Multi-Image Vision Agents via End2End Reinforcement Learning [51.81337984526068]
  We propose IMAgent, an open-source vision agent trained via end-to-end reinforcement learning.<n>By leveraging a multi-agent system, we generate challenging and visually-rich multi-image QA pairs.<n>We develop two specialized tools for visual reflection and confirmation, allowing the model to proactively reallocate its attention to image content.
  arXiv  Detail & Related papers  (2025-12-05T10:02:38Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
  Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
  arXiv  Detail & Related papers  (2025-10-06T10:44:04Z)
• Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration [63.90193684394165]
  We introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation.<n>During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards.<n>During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step.
  arXiv  Detail & Related papers  (2025-05-29T07:24:37Z)
• MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding [40.52017994491893]
  MDocAgent is a novel RAG and multi-agent framework that leverages both text and image.<n>Our system employs five specialized agents: a general agent, a critical agent, a text agent, an image agent and a summarizing agent.<n>Preliminary experiments on five benchmarks demonstrate the effectiveness of our MDocAgent, achieve an average improvement of 12.1%.
  arXiv  Detail & Related papers  (2025-03-18T06:57:21Z)
• AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning [93.96463520716759]
  Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and hallucinations. Here, we introduce AvaTaR, a novel and automated framework that optimize an LLM agent to effectively leverage provided tools, improving performance on a given task.
  arXiv  Detail & Related papers  (2024-06-17T04:20:02Z)

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.