12 papers
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Jialuo Chen, Lingqi Jiang, Xinhao Deng +7
Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We introduce PoisonedEvolution, a…
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
Jialuo Chen, Minghe Wang, Lingqi Jiang +7
LLM-agent ecosystems are rapidly growing around reusable skills: mixed-modality packages of metadata, natural-language instructions, code, tools, references, and operational workfl…
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Yunhao Feng, Ruixiao Lin, Ming Wen +12
LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed sa…
VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills
Ying Li, Yanju Chen, Hongbo Wen +5
Agentic systems increasingly act through third-party skills, allowing model-generated decisions to affect files, communication channels, and cyber-physical devices. These skills of…
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Ruixiao Lin, Xinhao Deng, Qingming Li +12
Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversa…
Constitutional On-Policy Safe Distillation
Ming Wen, Yuxuan Liu, Kun Yang +9
On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervis…