Story
arxiv_agent_systems_research ยท Oct 28, 2026 ยท paper
arxiv.orgOct 28, 2026
original source linked
In brief
Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates a system but only observes and learns from its...
Feed lens
agenteval