Saved in:
Bibliographic Details
Main Authors: Câmara, Arthur, Slot, Vincent, Zavrel, Jakub
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.02988
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Given a user's complex information need, a multi-agent Deep Research system iteratively plans, retrieves, and synthesizes evidence across hundreds of documents to produce a high-quality answer. In one possible architecture, an orchestrator agent coordinates the process, while parallel worker agents execute tasks. Current Deep Research systems, however, often rely on hand-engineered prompts and static architectures, making improvement brittle, expensive, and time-consuming. We therefore explore various multi-agent optimization methods to show that enabling agents to self-play and explore different prompt combinations can produce high-quality Deep Research systems that match or outperform expert-crafted prompts.