自進化智能體安全隱患

Computer Science > Artificial Intelligence arXiv:2608.

12851 (cs) [Submitted on 13 Aug 2026] Title:Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents Authors:Xutao Mao, Liangjie Zhao, Xiang Zheng, Cong Wang View a PDF of the paper titled Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents, by Xutao Mao and Liangjie Zhao and Xiang Zheng and Cong Wang View PDF HTML (experimental) Abstract:Self-improving LLM agents convert successful trajectories into persistent cross-task state.

An unsafe success can thereby become reusable policy after its triggering input disappears.Skill evolution makes this failure measurable by distilling operational trajectories into executable, transferable, and inspectable procedures.

Because evolution optimizes task outcomes rather than procedure safety, compromised experience can cause skill misevolution.Existing benchmarks measure current behavior or static artifacts but cannot attribute risk across authoring, retrieval, and later execution.

To expose this lifecycle, we introduce SkillMisevo-Gym, a lifecycle-aware harness that versions skill state across agent frameworks, and SkillMisevo-Bench, a frozen design from malicious exposure to carryover tasks, with concept-aligned benign tasks and nine lifecycle metrics.

We also introduce SafeEvolve, a wrapper that repairs unsafe content and governs subsequent reuse.Across 25 agent-method configurations, each covering 525 tasks in 25 episodes, all 21 evolved configurations author unsafe artifacts, while only fifteen lead to fresh-session harm.

In the exposure sweep, three malicious tasks raise carryover ASR from 16.0% to 35.3%.Across representative skill evolution methods, SafeEvolve reduces unsafe retrieval and fresh-session harm by 26.7 and 17.3 percentage points, respectively, while mean benign utility changes by only 0.4 points.

Together, persistent-adaptation safety must govern what updates write and what future executors reuse.Code is available at this https URL.Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2608.12851 [cs.AI] (or arXiv:2608.12851v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.

12851 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Xutao Mao [view email] [v1] Thu, 13 Aug 2026 05:47:43 UTC (1,008 KB) Full-text links: Access Paper: View a PDF of the paper titled Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents, by Xutao Mao and Liangjie Zhao and Xiang Zheng and Cong WangView PDFHTML (experimental)TeX Source view license Current browse context: cs.

AI < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading...BibTeX formatted citation × loading...

Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.

ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?

) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.

AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?

) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.Which authors of this paper are endorsers?| Disable MathJax (What is MathJax?)