IEMAS: An Incentive-Efficiency Routing Framework for Open Agentic Web Ecosystems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917351270645760 |
|---|---|
| author | Liu, Hongze Guo, Chang Li, Yingzeng Wang, Mengru Lou, Jiong Yuan, Shijing Zhou, Hefeng Wu, Chentao LI, Jie |
| author_facet | Liu, Hongze Guo, Chang Li, Yingzeng Wang, Mengru Lou, Jiong Yuan, Shijing Zhou, Hefeng Wu, Chentao LI, Jie |
| contents | 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 uncertainty, which feeds into a VCG-based bipartite matching mechanism. This design guarantees truthful capability reporting and social optimality while explicitly leveraging KV cache-affinity to minimize computational redundancy. We implement IEMAS on top of vLLM and evaluate it via extensive simulations. Results demonstrate that our incentive-efficiency co-design reducing average service cost by 35% and end-to-end latency by up to 2.9
compared to baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17302 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IEMAS: An Incentive-Efficiency Routing Framework for Open Agentic Web Ecosystems Liu, Hongze Guo, Chang Li, Yingzeng Wang, Mengru Lou, Jiong Yuan, Shijing Zhou, Hefeng Wu, Chentao LI, Jie Networking and Internet Architecture Computer Science and Game Theory 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 uncertainty, which feeds into a VCG-based bipartite matching mechanism. This design guarantees truthful capability reporting and social optimality while explicitly leveraging KV cache-affinity to minimize computational redundancy. We implement IEMAS on top of vLLM and evaluate it via extensive simulations. Results demonstrate that our incentive-efficiency co-design reducing average service cost by 35% and end-to-end latency by up to 2.9 compared to baselines. |
| title | IEMAS: An Incentive-Efficiency Routing Framework for Open Agentic Web Ecosystems |
| topic | Networking and Internet Architecture Computer Science and Game Theory |
| url | https://arxiv.org/abs/2603.17302 |