累積的・監査付きガードレールツール進化によるLLMエージェントの安全性
Cumulative and Audited Guardrail Tool Evolution for LLM Agent Safety
LLMエージェントの安全対策を、継承・監査・改良を繰り返す実行可能なガードレールツールとして自己進化させるフレームワークEVOLVEを提案し、複数ベンチマークで既存手法を平均F1で22%上回った。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Xiao Yang, Aishan Liu, Siyuan Liang, Zonghao Ying, Le Wang, Jiakai Wang, Xianglong Liu, Dacheng Tao
分類: cs.AI
原文アブストラクト
Large language model (LLM) agents increasingly operate in open-world environments where safety risks cannot be fully predefined. However, most existing guardrail mechanisms remain static, relying on fixed rules, prompts, or classifiers that generalize poorly to emerging risks. Here we present EVOLVE, a tool-level self-evolving defense framework that formulates agent security as a process of cumulative security evolution. Inspired by how human societies transform experiences into transferable protective knowledge, EVOLVE externalizes security knowledge into executable guardrail tools that are continuously inherited, independently audited, and iteratively refined through lifelong interaction. Across multiple benchmarks, backbone models, and embodied environments, EVOLVE consistently outperforms existing defenses across diverse risk scenarios with +22\% average F1 score. We further validate the framework in real-world robotic and autonomous agent systems. Our results suggest that scalable agent safety may require continuously evolving defense systems rather than static guardrails.