AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Secure Multi-agent Reinforcement Learning for Service Systems with Affinity and Byzantine Nodes: Stability Analysis and Protection Design

Yifan Jiang, Pan Jiasheng, Mengtian Li, Li Jin

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add W-MSR aggregation and synchronized policy mixture under Byzantine attackdecentralized actor-critic MARL · LLM semantic routingaverage service time per task: 4.46e+5 -> 6.88Improved
add W-MSR aggregation and synchronized policy mixture under Byzantine attackdecentralized actor-critic MARL · Multi-agent edge computingaverage service time per task: 18.16 -> 4.13Improved
add W-MSR aggregation and synchronized policy mixture under Byzantine attackdecentralized actor-critic MARL · Smart manufacturing deliveryaverage service time per task: 36.28 -> 4.48Improved
add defense under Byzantine attackdecentralized actor-critic MARL · LLM semantic routinglearned affinity: 0.472 -> 0.664Improved
add defense under Byzantine attackdecentralized actor-critic MARL · Multi-agent edge computinglearned affinity: 0.351 -> 0.642Improved
add defense under Byzantine attackdecentralized actor-critic MARL · Smart manufacturing deliverylearned affinity: 0.409 -> 0.580Improved
add synchronized policy mixture on top of W-MSR (ablation)resilient MARL · LLM, MEC, deliveryqueue stabilityImproved
add W-MSR on top of policy mixture (ablation)resilient MARL · LLM, MEC, deliverylearning qualityImproved
use proposed method versus mean, median, projection aggregationresilient MARL · MECperformance under Byzantine attackImproved
use proposed method versus robust aggregation baselinesresilient MARL · LLM routingperformance under Byzantine attackNo clear effect
use proposed method versus robust aggregation baselinesresilient MARL · Smart manufacturing deliveryperformance under Byzantine attackNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy