AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning

ArXi:2605.24486v1 Announce Type: new Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and effective scaffolding. In contrast, much less is understood about scaling out: whether multiple peer agents, all targeting the same task, can become an additional source of capability without relying on explicit role specialization or workflow orchestration. We study this question and propose AgentFugue, a collective reasoning framework built around a shared reasoning hub.