OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
This work addresses a critical bottleneck in multi-agent LLM collaboration for applications requiring complex reasoning and problem-solving, offering a novel intermediate layer to enhance cognitive synergy.
The paper tackles the problem of inefficient linguistic interactions for deep collaboration among expert agents in multi-agent LLM systems by introducing OSC, a knowledge-aware adaptive collaboration framework that uses Collaborator Knowledge Models for dynamic cognitive state perception and real-time gap analysis, resulting in significant improvements in task performance and communication efficiency on complex reasoning benchmarks.
This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with large language models. While prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. OSC addresses this gap as a pivotal intermediate layer between selection and aggregation, introducing Collaborator Knowledge Models (CKM) to enable each agent to dynamically perceive its collaborators' cognitive states. Through real-time cognitive gap analysis, agents adaptively adjust communication behaviors, including content focus, detail level, and expression style, using learned strategies. Experiments on complex reasoning and problem-solving benchmarks demonstrate that OSC significantly improves task performance and communication efficiency, transforming "parallel-working individuals'' into a "deeply collaborative cognitive team.'' This framework not only optimizes multi-agent collaboration but also offers new insights into LLM agent interaction behaviors.