Autonomous agents in safety-critical applications must continuously adapt to dynamic conditions without compromising performance and reliability. This work introduces TAPA (Training-free Adaptation of Programmatic Agents), a novel framework that positions large language models (LLMs) as intelligent moderators of the symbolic action space. Unlike prior programmatic agents typically generate a monolithic policy program or rely on fixed symbolic action sets, TAPA synthesizes and adapts modular programs for individual high-level actions, referred to as logical primitives. By decoupling strategic intent from execution, TAPA enables meta-agents to operate over an abstract, interpretable action space while the LLM dynamically generates, composes, and refines symbolic programs tailored to each primitive. Extensive experiments across cybersecurity and swarm intelligence domains validate TAPA's effectiveness. In autonomous DDoS defense scenarios, TAPA achieves 77.7% network uptime while maintaining near-perfect detection accuracy in unknown dynamic environments. In swarm intelligence formation control under environmental and adversarial disturbances, TAPA consistently preserves consensus at runtime where baseline methods fail. This work promotes a paradigm shift for autonomous system design in evolving environments, from policy adaptation to dynamic action adaptation.

翻译：安全关键应用中的自主智能体必须在动态条件下持续自适应，同时不牺牲性能与可靠性。本文提出TAPA（程序化智能体免训练自适应框架），该创新框架将大语言模型（LLM）定位为符号动作空间的智能调节器。与通常生成单一策略程序或依赖固定符号动作集的传统程序化智能体不同，TAPA针对独立高层动作（称为逻辑基元）合成并适配模块化程序。通过将战略意图与执行解耦，TAPA使元智能体能在抽象、可解释的动作空间上运行，而LLM则动态生成、组合并优化为每个基元定制的符号程序。在网络安全和群体智能领域的广泛实验验证了TAPA的有效性：在自主DDoS防御场景中，TAPA在未知动态环境下实现77.7%的网络正常运行时间，同时保持接近完美的检测准确率；在环境干扰与对抗扰动下的群体智能编队控制任务中，TAPA能持续维持运行时共识，而基线方法均告失效。这项工作推动了动态环境中自主系统设计范式的转变——从策略适应转向动态动作适应。