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

TL;DR

This paper introduces WideSeek-R1, a multi-agent reinforcement learning framework that enhances broad information seeking by scaling width through parallel subagents, achieving competitive performance and demonstrating the benefits of width scaling.

Contribution

Proposes WideSeek-R1, a multi-agent RL framework that effectively scales width for broad information seeking, outperforming traditional hand-crafted multi-agent systems.

Findings

WideSeek-R1-4B achieves 40.0% item F1 on WideSearch benchmark.

Performance improves with increasing number of parallel subagents.

WideSeek-R1's approach is comparable to single-agent models with much larger parameters.

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.