Evolution Under Fire: Evolving Agent Safety Harnesses with Adaptive Injection Stressors
Tool-using language-model agents must act on information from untrusted emails, webpages, and documents. This creates a central security challenge: malicious instructions and legitimate task directives can arrive through the same interaction channel. Existing defenses are largely hand-designed and static, making further improvements dependent on repeated manual redesign. We introduce Evolution Under Fire, a staged framework that couples safety-harness evolution with adaptive stressor evolution. Utility-constrained, Pareto-scheduled tree search evolves complete executable safety harnesses from execution evidence while keeping the task model, benchmark, tools, and evaluator fixed. Adaptive stressor evolution then discovers utility-preserving attacks that guide a subsequent stage of harness evolution. On AgentDyn with GPT-4o-mini, an evolved harness reduces attack success from 50.4% to 3.0%, improves clean and attacked utility over the initial harness, and offers a stronger security-utility trade-off than reproduced defenses. On Agent-SafetyBench with Qwen2.5-7B-Instruct, harness evolution reduces attack success from 82.6% to 62.0% while retaining helpfulness and runtime validity. Evolved harnesses also transfer without further evolution to Qwen3.5-35B-A3B, reducing attack success from 32.1% to 0.9% while improving attacked-task utility.
Authors
- Krishna Kanth Nakka (ORCID: https://orcid.org/0000-0002-2381-6593)
- Yujun Wang
- Hinrich Sch{ü}tze
- Jinhe Bi
- Xuebing Zhou
- Yunpu Ma
- Yilun Liu
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.48550/arxiv.2611.22583
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- preprint