Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
Paper • 2605.02801 • Published • 9
Jheng-Hong (Matt) Yang
justram
AI & ML interests
Consulting, Engineering, and Technical Services around DataSys | I like search 🔍
Recent Activity
upvoted a paper 17 days ago
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces upvoted a paper 28 days ago
Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient? updated a collection 29 days ago
Pi-SeriniOrganizations
