{"ID":2873932,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05651","arxiv_id":"2509.05651","title":"Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks","abstract":"Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination and reflective benchmarking to optimize global task performance. Orchestrator introduces a monitoring mechanism to track agent-environment dynamics, using active inference benchmarks to optimize system behavior. By tracking agent-to-agent and agent-to-environment interaction, Orchestrator mitigates the effects of partial observability and enables agents to approximate global task solutions more efficiently. We evaluate the framework on a series of maze puzzles of increasing complexity, demonstrating its effectiveness in enhancing coordination and performance in dynamic, non-linear environments with long-horizon objectives.","short_abstract":"Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination and reflective benchmarking to optimize global task performance. Orchestrator i...","url_abs":"https://arxiv.org/abs/2509.05651","url_pdf":"https://arxiv.org/pdf/2509.05651v1","authors":"[\"Lukas Beckenbauer\",\"Johannes-Lucas Loewe\",\"Ge Zheng\",\"Alexandra Brintrup\"]","published":"2025-09-06T09:03:36Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}