跳到正文
arXiv cs.CL· Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon, Chanjun Park·· 10 小时前AI 评分38

EvoSkill Injection:针对自进化智能体自主技能生成与演化的红队测试

EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents

AI 导读

研究者提出 EvoSkill Injection 威胁模型,针对自进化智能体自主生成、精炼和复用技能的流程,并给出红队框架 SARGE,通过迭代生成、升级与强化交互评估该威胁。

正文 · 原文

View PDF HTML (experimental)

Abstract:LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution. Recent studies propose self-evolving agents that autonomously generate, refine, and reuse skills from past experiences to enable continuous capability evolution. However, autonomous skill evolution introduces a new attack surface in which malicious capabilities are generated, stored, and reused as legitimate skills. In this paper, we define EvoSkill Injection as a threat model targeting the autonomous skill generation and evolution pipeline of self-evolving agents. We further propose SARGE (Red-teaming Autonomous Skill Generation and Evolution in self-evolving agents), a red-teaming framework for evaluating this threat model through iterative generation, escalation, and reinforcement interactions. To support our framework, we construct EvoSkillBench, a benchmark dataset of malicious interaction trajectories for inducing malicious skill formation in self-evolving agents, and introduce EvoSkillSafetyBench, a post-attack benchmark for evaluating whether injected malicious skills are subsequently retrieved and activated as harmful behaviors. Our evaluation shows that SARGE induces malicious skill formation and that injected skills are persistently stored and repeatedly activated, highlighting the risk of persistent capability corruption.
Comments: Accepted to EMNLP 2026
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2608.30429 [cs.AI]
  (or arXiv:2608.30429v2 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2608.30429

arXiv-issued DOI via DataCite

Submission history

From: Doyun Kim [view email]
[v1] Mon, 31 Aug 2026 08:25:03 UTC (285 KB)
[v2] Thu, 19 Nov 2026 13:21:55 UTC (286 KB)

来源:arXiv cs.CL · arxiv.org