[2510.26585] Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems

Computer Science > Multiagent Systems arXiv:2510.26585 (cs) [Submitted on 30 Oct 2025 (v1), last revised 2 Mar 2026 (this version, v2)] Title:Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems Authors:Fulin Lin, Shaowen Chen, Ruishan Fang, Hongwei Wang, Tao Lin View a PDF of the paper titled Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems, by Fulin Lin and 4 other authors View PDF HTML (experimental) Abstract:While Multi-Agent Systems (MAS) excel at complex tasks, their growing autonomy with operational complexity often leads to critical inefficiencies, such as excessive token consumption and failures arising from misinformation. Existing methods primarily focus on post-hoc failure attribution, lacking proactive, real-time interventions to enhance robustness and efficiency. To this end, we introduce SupervisorAgent, a lightweight and modular framework for runtime, adaptive supervision that operates without altering the base agent's architecture. Triggered by an LLM-free adaptive filter, SupervisorAgent intervenes at critical junctures to proactively correct errors, guide inefficient behaviors, and purify observations. On the challenging GAIA benchmark, SupervisorAgent reduces the token consumption of the Smolagent framework by an average of 29.68% without compromising its success rate. Extensive experiments across five additional benchmarks (math reasoning, code generation, and question answering) and various SoTA foundation mod...