On Safety Risks in Experience-Driven Self-Evolving Agents

ACL ARR 2026 January Submission7404 Authors

Keywords: Self-Evolving Agent, AI Safety

Abstract: Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. In this study, we investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments. Notably, experience gathered solely from benign tasks can still compromise safety in high-risk scenarios. Further analysis attributes this degradation to the execution-oriented nature of accumulated experience, which reinforces agents' tendency to act rather than refuse. In more realistic settings where agents encounter both benign and harmful tasks, refusal-related experience mitigates safety decline but induces over-refusal, revealing a fundamental safety–utility trade-off. Overall, our findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: Self-Evolving Agent, AI Safety

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 7404