Recursive Multi-Agent Systems
- Published
- Source
- arXiv
- Paper number
- 163
- Field
- Agents / Multi-Agent / Efficiency
- arXiv ID
- 2604.25917
Key points
- A single LLM often struggles on complex tasks that require broad reasoning or diverse expertise.
- Existing multi-agent systems (MAS) rely on explicit text-based interaction, which causes high latency, increased token usage, and gradient instability when optimizing at the system level.
- Optimizing the entire set of agents in an MAS through training is computationally expensive, while prompt-based adaptation has limited ability to improve the core capabilities of the agents.
- The paper develops RecursiveMAS, a framework that formulates the entire multi-agent system as unified latent-space recursive computation for iterative refinement of collaborative reasoning.
- It introduces lightweight residual RecursiveLink modules, with inner modules for within-agent communication and outer modules for between-agent communication, to enable efficient latent-state transfer and refinement among agents.
- It implements a two-stage inner-outer loop training algorithm that freezes the base LLM parameters and optimizes only RecursiveLink, which promotes stable system-level co-optimization.
Paper links
External research summaries. These are not HDATF publications or measured product results.