AI Paper Atlas

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

VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement Learning

Qian Zhang, Zhuo Sun, Yao Zhang, Zhiwen Yu, Bin Guo, Jun Zhang

AAAI 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Learned inter-agent communication · 2 citations (OpenAlex)

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 ResoNet VoI-aware resource allocation (ablation)VIL2C · SMACv2 10gen terranwin rate: 0.28 -> 0.55Improved
add ResoNet VoI-aware resource allocation (ablation)VIL2C · SMACv2 10gen zergwin rate: 0.41 -> 0.48Improved
add Progressive Reception (ablation)VIL2C · SMACv2 10gen protosswin rate: 0.32 -> 0.42Improved
add Progressive Reception (ablation)VIL2C · SMACv2 10gen zergwin rate: 0.28 -> 0.48Improved
add naive communication (I2C, equal allocation) to MAPPO under latencyMAPPO · Predator-PreyrewardHurt
VIL2C instead of baselines under latencyMAPPO with communication · Predator-Prey, Cooperative NavigationrewardImproved
increase maximum waiting time (ablation)VIL2C · Predator-PreyrewardMixed
reduce bandwidth/power budget (ablation)VIL2C · Predator-PreyrewardHurt

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