Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks
This addresses coordination problems in multi-agent systems for complex, dynamic environments, but it appears incremental as it builds on existing active inference and attention mechanisms.
The paper tackles the challenge of partial observability and suboptimal coordination in LLM-enhanced multi-agent systems for long-horizon tasks by proposing Orchestrator, a framework that uses attention-inspired coordination and reflective benchmarking, showing effectiveness in enhancing coordination and performance on maze puzzles of increasing complexity.
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.