Self-Optimizing Multi-Agent Systems for Deep Research
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915912939995136 |
|---|---|
| author | Câmara, Arthur Slot, Vincent Zavrel, Jakub |
| author_facet | Câmara, Arthur Slot, Vincent Zavrel, Jakub |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02988 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Self-Optimizing Multi-Agent Systems for Deep Research Câmara, Arthur Slot, Vincent Zavrel, Jakub Information Retrieval Artificial Intelligence 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. |
| title | Self-Optimizing Multi-Agent Systems for Deep Research |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2604.02988 |