WideSeek: Advancing Wide Research via Multi-Agent Scaling

2026-02-02

AI Summary

This work addresses the lack of dedicated benchmarks and optimization methods for wide research—a paradigm requiring efficient, parallel acquisition and synthesis of multi-source information under complex constraints. To this end, we propose WideSeek, a novel framework that introduces WideSeekBench, the first benchmark dataset tailored for wide research, and a dynamic forked hierarchical multi-agent architecture capable of spawning parallel sub-agents at runtime. We further incorporate multi-agent trajectory linearization and end-to-end reinforcement learning to enable unified training. Experimental results demonstrate that scaling the number of agents substantially enhances the system’s capacity for information synthesis in complex tasks, with WideSeek significantly outperforming existing baselines across multiple evaluation metrics.

Technology Category

• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the lack of dedicated benchmarks and optimization methodologies for search breadth. To address these challenges, we take a deep dive into Wide Research from two perspectives: Data Pipeline and Agent Optimization. First, we produce WideSeekBench, a General Broad Information Seeking (GBIS) benchmark constructed via a rigorous multi-phase data pipeline to ensure diversity across the target information volume, logical constraints, and domains. Second, we introduce WideSeek, a dynamic hierarchical multi-agent architecture that can autonomously fork parallel sub-agents based on task requirements. Furthermore, we design a unified training framework that linearizes multi-agent trajectories and optimizes the system using end-to-end RL. Experimental results demonstrate the effectiveness of WideSeek and multi-agent RL, highlighting that scaling the number of agents is a promising direction for advancing the Wide Research paradigm.

Problem

• Wide Research
• search breadth
• benchmark
• multi-agent scaling
• information seeking

Innovation

• Wide Research
• Multi-Agent System
• Reinforcement Learning
• Information Seeking Benchmark
• Dynamic Hierarchical Architecture