arXiv:2605.11732v2 Announce Type: replace-cross 
Abstract: 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.

يقدم المقال AgentDisCo، وهي بنية جديدة مصممة لوكلاء البحث العميق، والتي تفصل بين عمليات استكشاف المعلومات واستغلالها من خلال إطار تعاوني يتضمن وكيلًا ناقدًا ووكيلًا مولدًا. تهدف هذه الطريقة إلى تحسين كفاءة وفعالية توليد تقارير البحث من خلال تحسين المخططات واستعلامات البحث بشكل متكرر.

El artículo presenta AgentDisCo, una nueva arquitectura diseñada para agentes de investigación profunda, que separa los procesos de exploración y explotación de información a través de un marco colaborativo que involucra un agente crítico y un agente generador. Este enfoque tiene como objetivo mejorar la eficiencia y efectividad de la generación de informes de investigación al refinar iterativamente los esquemas y las consultas de búsqueda.

L'article présente AgentDisCo, une nouvelle architecture conçue pour les agents de recherche approfondie, qui sépare les processus d'exploration et d'exploitation de l'information grâce à un cadre collaboratif impliquant un agent critique et un agent générateur. Cette approche vise à améliorer l'efficacité et l'efficience de la génération de rapports de recherche en affinant itérativement les plans et les requêtes de recherche.

The paper introduces AgentDisCo, a novel architecture designed for deep research agents, which separates the processes of information exploration and exploitation through a collaborative framework involving a critic and a generator agent. This approach aims to enhance the efficiency and effectiveness of research report generation by iteratively refining outlines and search queries.