WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiao, Zile, Chen, Guoxin, Chen, Xuanzhong, Yu, Donglei, Yin, Wenbiao, Wang, Xinyu, Zhang, Zhen, Li, Baixuan, Yin, Huifeng, Li, Kuan, Min, Rui, Liao, Minpeng, Jiang, Yong, Xie, Pengjun, Huang, Fei, Zhou, Jingren
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918144737542144
author Qiao, Zile
Chen, Guoxin
Chen, Xuanzhong
Yu, Donglei
Yin, Wenbiao
Wang, Xinyu
Zhang, Zhen
Li, Baixuan
Yin, Huifeng
Li, Kuan
Min, Rui
Liao, Minpeng
Jiang, Yong
Xie, Pengjun
Huang, Fei
Zhou, Jingren
author_facet Qiao, Zile
Chen, Guoxin
Chen, Xuanzhong
Yu, Donglei
Yin, Wenbiao
Wang, Xinyu
Zhang, Zhen
Li, Baixuan
Yin, Huifeng
Li, Kuan
Min, Rui
Liao, Minpeng
Jiang, Yong
Xie, Pengjun
Huang, Fei
Zhou, Jingren
contents Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
Qiao, Zile
Chen, Guoxin
Chen, Xuanzhong
Yu, Donglei
Yin, Wenbiao
Wang, Xinyu
Zhang, Zhen
Li, Baixuan
Yin, Huifeng
Li, Kuan
Min, Rui
Liao, Minpeng
Jiang, Yong
Xie, Pengjun
Huang, Fei
Zhou, Jingren
Computation and Language
Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.
title WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
topic Computation and Language
url https://arxiv.org/abs/2509.13309