In multi-robot manipulation, an action's value depends on how teammates respond. We present \method{} (Cooperative Action--Response Belief Estimation), a framework for learning \emph{team-response beliefs} from local history. A predictive belief encoder represents the interaction and conditions a nominal action. Matche...
Zi-Hao Li, Ya-Nan Zhou, Ran-Peng Qiu et al.· 0 citations
This work introduces CoRE, which learns Collaboration-Role Experts from pooled multi-task, multi-robot demonstrations, and achieves the highest average performance among evaluated decentralized methods.
Ya-Nan Zhou, Zhao-Yan Qian, Zi-Hao Li et al.· 1 citation
This survey synthesizes agentic reasoning methods into a unified roadmap bridging thought and action, and outlines open challenges and future directions, including personalization, long-horizon interaction, world modeling, scalable multi-agent training, and governance for real-world deployment.
Tian-Xin Wei, Ting-Wei Li, Zhining Liu et al.· 39 citations· ⚡6
This work introduces TRAjectory-routed Causal Evidence (TRACE), a memory framework for visuomotor imitation policies that stores task-relevant visual and robot-state evidence in a fixed-size latent memory that remains bounded over long episodes.
