Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

  • 类型：arxiv
  • 标识：2608.17253
  • 链接：https://arxiv.org/abs/2608.17253
  • 主分类：agent
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar
  • S2被引：0
  • 影响力被引：0
  • TLDR：This work introduces Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers, and shows that unsupervised reasoning can emerge through cooperative multi-agent training.
  • 副分类：multimodal
  • 待LLM分类：否
  • 标题中文：Co-RL：无监督推理在多智能体强化学习中从多样化群体中涌现
  • TLDR中文：本文提出 Co-RL，一种由多个解耦模型组成的框架，这些模型不共享参数，通过基于彼此输出奖励的强化学习同时进行优化，并表明无监督推理可以通过协作式多智能体训练涌现
  • 来源文件：
  • /inbox/tom/_candidates/2026-08-20-agent-rag-longcontext-candidates.json
  • [S2 enrich]