PoisonedEvolution is introduced, a trajectory-poisoning attack on self-evolving skill systems that exposes evidence promotion as a security boundary for self-evolving agents.
Jia-Luo Chen, Ling-Qi Jiang, Xin-Hao Deng et al.· 1 citation· ⚡1
SKILLTRACE is presented, a multi-trace provenance auditing framework for LLM-agent skill reuse that represents the Operational Trace as a Skill Operational Graph (SOG) that captures activation, procedure, and resource-flow structure.
Jia-Luo Chen, Minghe Wang, Lingqi Jiang et al.· 0 citations
VeRe is proposed, a verification-guided repair framework that leverages linear relaxation to precisely and efficiently estimate the repair significance of neurons and synthesizes ideal intervals that provide sound guarantees for correct behaviors, thereby facilitating surgical and targeted adjustments of neuron paramet...
Jia-Nan Ma, Wei Chen, Pengfei Yang et al.· ACM Transactions on Software...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.