IEMAS: An Incentive-Efficiency Routing Framework for Open Agentic Web Ecosystems
Hongze Liu, Chang Guo, Yingzeng Li, Mengru Wang, Jiong Lou, Shijing Yuan, Hefeng Zhou, Chentao Wu, Jie LI

TL;DR
IEMAS is a distributed incentive-based framework for multi-agent web ecosystems that optimizes resource reuse and system efficiency, reducing costs and latency through a novel matching mechanism and predictive modeling.
Contribution
It introduces a novel incentive-efficiency co-design framework that incorporates probabilistic QoS prediction and KV cache-awareness for multi-agent systems.
Findings
Reduced average service cost by 35%
Lowered end-to-end latency by up to 2.9x
Demonstrated effectiveness through extensive simulations
Abstract
The transition to open, distributed Multi-Agent Systems (MAS) promises scalable intelligence but introduces a non-trivial tension: maximizing global efficiency requires cooperative, resource-aware scheduling, yet autonomous agents may be self-interested and cannot be managed by a centralized controller. Prior approaches fall short in two key areas: they typically focus on single-query routing, neglecting long-term resource reuse (e.g., KV-caching) and the complexities of system-level many-to-many matching; furthermore, they rely on generic incentive mechanisms that ignore the distinct characteristics of LLM inference. To bridge this gap, we propose IEMAS (Incentive-Efficiency Mechanism for Multi-Agent Systems), a distributed framework that aligns economic incentives with system performance. IEMAS integrates a probabilistic predictive model to estimate Quality of Service (QoS) under…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCaching and Content Delivery · Peer-to-Peer Network Technologies · Cloud Computing and Resource Management
