RESEARCH

Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints

ArXiv cs.AI · Wed, 20 May 2026 04:00:00 GMT

arXiv:2605.19140v1 Announce Type: new Abstract: We study workflow learning in a setting where specialized agents hand off control through a shared artifact, each agent observes only a local function of that artifact and its own private state, and no centralized learner accesses j

Read original source Discuss with A.S.I.S