3 papers
cs.MA2026
Reachability-Certified Subteam Decomposition for Locally Interacting Multi-Agent MDPs
Xiangwu Wang, Chengwei Cao, Hongyuan Tang
Persistent communication limits force a multi-agent system to decide which agents may coordinate throughout a rollout. Current proximity alone is insufficient: separated agents may…
cs.MA2026
Rank Without an Oracle: Deviation-Aware Interaction-Rank Selection from Offline Multi-Agent Logs
Xiangwu Wang, Chengwei Cao, Hongyuan Tang
Offline multi-agent payoff models are estimated under a logging distribution but used on distributions induced by learned solutions and unilateral deviations. Standard held-out los…
cs.LG2026
Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data
Xiangwu Wang, Chengwei Cao, Yicheng Song +2
Adaptive gradient methods can favor max-margin separators that differ from gradient descent, yet a fixed positive numerical stability constant eventually changes the update geometr…