Agents
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
arXiv:2608.12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as
arXiv:2608.12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses rely heavily on manually designed interventions and lack a principled framework for their construction and maintenance. In this work, we first develop a harness-level formulation of runtime defense that systematically characterizes how harness mechanisms enable defense construction and provides a unified view of existing runtime defense interventions from a harness perspective. Building on this formulation, we propose HARD (Harness-based Autonomous Runtime Defense Evolution), a self-evolving runtime defense framework that automatically identifies appropriate intervention strategies and iteratively improves defense artifacts based on observed failure traces. HARD transforms runtime defense development from manual engineering into an autonomous evolution process, and extensive experiments demonstrate that it improves security performance over existing handcrafted defenses while preserving benign task utility. Our findings highlight autonomous defense evolution as a promising new paradigm for securing deployed LLM agents, enabling agents to identify defense weaknesses and continuously improve their protection mechanisms.
Related
- LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity
- Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
- AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
- Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study
- Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
Source: arXiv cs.AI | 2026-08-14