WideSeek-R1-4b/README.md

license, language, base_model, library_name, pipeline_tag, tags, metrics, model-index

license	language	base_model	library_name	pipeline_tag	tags	metrics	model-index
apache-2.0	en	Qwen/Qwen3-4B	transformers	text-generation	arxiv:2602.04634	accuracy	name results WideSeek-R1-4B task dataset metrics type WideSearch type name WideSearch WideSearch type value accuracy 40.0

WideSeek-R1-4B

🌐 Project Page | 📄 Paper | 📖 Doc | 💻 Code | 📦 Dataset | 🤗 Models

Overview

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.

For more details, see our project page

Citation

If you use this model in your research, please cite our paper:

@article{xu2026wideseek,
  title   = {WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning},
  author  = {Xu, Zelai and Xu, Zhexuan and Zhang, Ruize and Zhu, Chunyang and Yu, Shi and Liu, Weilin and Zhang, Quanlu and Ding, Wenbo and Yu, Chao and Wang, Yu},
  journal = {arXiv preprint arXiv:2602.04634},
  year    = {2026},
}