Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

2026-08-13

AI Summary

Current runtime defenses for large language model (LLM) agents rely on manually crafted mechanisms, lacking a systematic framework for construction and continuous optimization, which limits their effectiveness against complex security threats. This work proposes HARD—a harness-based formal framework for runtime defense that reframes the defense problem as a systematic task at the harness level. HARD automatically identifies intervention strategies through failure trajectory analysis and iteratively refines defense artifacts, enabling autonomous evolution of protective mechanisms. Experimental results demonstrate that HARD significantly enhances security while preserving benign task utility, outperforming existing handcrafted approaches and establishing a novel paradigm for self-evolving defenses in LLM agents.

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.

Problem

• runtime defense
• LLM agents
• security threats
• handcrafted interventions
• autonomous evolution

Innovation

• self-evolving defense
• runtime defense
• harness-based formulation
• autonomous security
• LLM agent security