Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems
- Published
- Source
- arXiv
- Paper number
- 119
- Field
- Agents / Architecture
- arXiv ID
- 2602.03695
Key points
- Existing multi-agent systems, or MAS, suffer from task specificity, high design overhead, and low reuse across different problem settings.
- Communication between agents, usually through natural language, can become unstable, accumulate errors, and lose information during long, multi-step interactions.
- Current MAS designs often lack truly reusable, task-agnostic internal abstractions for organizing multi-agent operations.
- The paper introduces Agent Primitives, three reusable latent building blocks, namely Review, Voting & Selection, and Planning & Execution, that encapsulate common multi-agent operation patterns.
- It implements inter-agent communication using only Key-Value, or KV, cache transfer, which shares internal model representations directly without relying on explicit natural language.
- It also develops an LLM-based Organizer guided by a Knowledge Pool to automatically select and compose primitives for a given query, which simplifies MAS construction.
Paper links
External research summaries. These are not HDATF publications or measured product results.