AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Jiarui, Yan, Zexuan, Wang, Shijian, Jiao, Wenxiang, Lu, Yuan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909035383488512
author Jin, Jiarui
Yan, Zexuan
Wang, Shijian
Jiao, Wenxiang
Lu, Yuan
author_facet Jin, Jiarui
Yan, Zexuan
Wang, Shijian
Jiao, Wenxiang
Lu, Yuan
contents In this paper, we present AgentDisCo, a novel Disentangled and Collaborative agentic architecture that formulates deep research as an adversarial optimization problem between information exploration and exploitation. Unlike existing approaches that conflate these two processes into a single module, AgentDisCo employs a critic agent to evaluate generated outlines and refine search queries, and a generator agent to retrieve updated results and revise outlines accordingly. The iteratively refined outline is then passed to a downstream report writer that synthesizes a comprehensive research report. The overall workflow supports both handcrafted and automatically discovered design strategies via a meta-optimization harness, in which the generator agent is repurposed as a scoring agent to evaluate critic outputs and generate quality signals. Powerful code-generation agents (e.g., Claude-Code, Codex) systematically explore agent configurations and construct a policy bank, a structured repository of reusable design strategies, enabling the framework to self-refine without extensive human intervention. We evaluate AgentDisCo on three established deep research benchmarks (DeepResearchBench, DeepConsult, DeepResearchGym) using Gemini-2.5-Pro, achieving performance comparable to or surpassing leading closed-source systems. Observing that existing benchmarks inadequately reflect real-world user needs, we introduce GALA (General AI Life Assistants), a benchmark that mines latent research interests from users' historical browsing behavior. We further develop a rendering agent that converts research reports into visually rich poster presentations, and demonstrate an end-to-end product, AutoResearch Your Interest, which delivers personalized deep research recommendations derived from individual browsing histories.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11732
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
Jin, Jiarui
Yan, Zexuan
Wang, Shijian
Jiao, Wenxiang
Lu, Yuan
Information Retrieval
Computation and Language
Multiagent Systems
Multimedia
In this paper, we present AgentDisCo, a novel Disentangled and Collaborative agentic architecture that formulates deep research as an adversarial optimization problem between information exploration and exploitation. Unlike existing approaches that conflate these two processes into a single module, AgentDisCo employs a critic agent to evaluate generated outlines and refine search queries, and a generator agent to retrieve updated results and revise outlines accordingly. The iteratively refined outline is then passed to a downstream report writer that synthesizes a comprehensive research report. The overall workflow supports both handcrafted and automatically discovered design strategies via a meta-optimization harness, in which the generator agent is repurposed as a scoring agent to evaluate critic outputs and generate quality signals. Powerful code-generation agents (e.g., Claude-Code, Codex) systematically explore agent configurations and construct a policy bank, a structured repository of reusable design strategies, enabling the framework to self-refine without extensive human intervention. We evaluate AgentDisCo on three established deep research benchmarks (DeepResearchBench, DeepConsult, DeepResearchGym) using Gemini-2.5-Pro, achieving performance comparable to or surpassing leading closed-source systems. Observing that existing benchmarks inadequately reflect real-world user needs, we introduce GALA (General AI Life Assistants), a benchmark that mines latent research interests from users' historical browsing behavior. We further develop a rendering agent that converts research reports into visually rich poster presentations, and demonstrate an end-to-end product, AutoResearch Your Interest, which delivers personalized deep research recommendations derived from individual browsing histories.
title AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
topic Information Retrieval
Computation and Language
Multiagent Systems
Multimedia
url https://arxiv.org/abs/2605.11732