Self-Optimizing Multi-Agent Systems for Deep Research
This addresses the challenge of improving Deep Research systems for users needing complex information synthesis, though it appears incremental as it builds on existing multi-agent architectures.
The paper tackles the problem of brittle and expensive hand-engineered prompts in multi-agent Deep Research systems by exploring self-optimization methods, showing that agents can match or outperform expert-crafted prompts through self-play and exploration.
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.