2 papers
cs.AI2026
TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents
Yutong Zhi, Jie Zhang, Xiuqi Lu +2
As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the context that…
cs.CL2026
ZenGen: Social Mind for LLMs
ZenGen Team, Ao Xiang, Bi Jingping +57
As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track…