TRACE is presented, a training-free layer that treats re-entry as an eligibility decision rather than a storage or retrieval operation, reconciling a departure checkpoint against absence-period updates, resolving explicit and implicit invalidation, and releasing a bounded Return View only when it covers the returning r...
Wen-Jun Xiong, Shengtao Zhang, Shangding Gu et al.· 0 citations
Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which later decisions are made. We study how collective failure changes with harmful-agent fraction and society size in a controlled financial agent society, where agents commu...
Le-Jun Zhang, Sarah Lu-Liang, Xin Jiang et al.· 0 citations
This work proposes MARA, which predicts future loss trajectories with conditional flow matching and coordinates compute nodes through a cooperative multi-agent autoregressive policy and reduces remaining-resource prediction error relative to weighted least squares.
Han-Ye Zhao, Mu-Ning Wen, Yong Yu et al.· 0 citations
Memory-Aware Propagation and Link Enforcement Guard, MAPLE-Guard, a memory-link guard for memory-enabled MAS, suggests that memory-aware link enforcement covers a gap left by prompt-level and topology-level defenses.
Wen-Jun Xiong, Yi-Jin Zhou, Jia-Qian Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
