Author name: Boxuan Zhang, Jianing Zhu, Zeru Shi, Dongfang Liu, Ruixiang Tang

arXiv:2605.08715v2 Announce Type: replace-cross
Abstract: LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Exi…

arXiv:2605.08715v1 Announce Type: cross
Abstract: LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing wo…