Prime Intellect adds multi-agent training and evaluation to PRIME-RL
Original titleMulti-Agent Systems in PRIME-RL
AISummary
Prime Intellect's RL stack now supports multi-agent systems, letting users program interactions between agents, choose which roles learn, and assign credit across an episode. The release introduces Agent and Env abstractions and four example patterns: agentic judging, self-play, and user simulation. Multi-agent support ships today in verifiers 0.3.0 and prime-rl 0.8.0.
AIWhy it matters
The post explains the Agent and Env abstractions and four multi-agent patterns, showing how roles, credit assignment, and episodes can be programmed in one RL stack.
Source: Prime Intellect Blog · primeintellect.ai