AI 精选动态
智能评分 60
Skill-MAS：多智能体元技能进化
AI 推荐理由
不同于推理时或训练时方法，Skill-MAS 在不改变前端模型权重的前提下实现策略级元技能迁移，值得关注其迁移性和代码实现。核心解读
DAIR.AI 介绍了 Skill-MAS，一种多智能体系统的元技能进化方法，通过多轨迹展开和选择性反思的闭环，在不修改模型权重的情况下提升编排能力。该方法在四个基准测试和四种不同大语言模型上验证，进化出的元技能可迁移到未见过的任务和其他模型。核心创新在于将编排能力作为可进化的元技能，以策略级原则积累经验。
全文
elvis (@omarsar0) 转发了 DAIR.AI (@dair_ai) 的帖子：
// Evolving Meta-Skill for Multi-Agent Systems //
Can a multi-agent system get better at orchestration without touching a single weight?
Automatic MAS generation has been stuck between two bad options. Inference-time methods use frozen frontier models but never learn from past runs. Training-time methods learn but are capped by small-model capability.
Skill-MAS takes a third path.
It treats the orchestration capability as an evolvable Meta-Skill, refined through a closed loop of multi-trajectory rollout and selective reflection that distills experience into strategy-level principles rather than memorized traces.
Across four benchmarks and four different LLMs, the evolved Meta-Skills transfer to unseen tasks and other models, because the know-how lives in text at the strategy level, not in any one model's weights.
You keep the frontier model and still accumulate experience.
Paper: https://t.co/fn4J2Gz33M
Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c
