Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we propose a new abstraction called LogAct, where each agent is a deconstructed state machine playing a shared log. In LogAct, agentic actions are visible in the shared log before they are executed; can be stopped prior to execution by pluggable, decoupled voters; and recovered consistently in the case of agent or environment failure. LogAct enables agentic introspection, allowing the agent to analyze its own execution history using LLM inference, which in turn enables semantic variants of recovery, health check, and optimization. In our evaluation, LogAct agents recover efficiently and correctly from failures; debug their own performance; optimize token usage in swarms; and stop all unwanted actions for a target model on a representative benchmark with just a 3% drop in benign utility.

翻译：智能体是基于大语言模型驱动的组件，能够以强大且任意的方式改变环境状态。由于异步性和故障的存在，在生产环境中对智能体执行过程提供保障极具挑战性。本文提出一种名为LogAct的新抽象机制，其中每个智能体作为面向共享日志的解构状态机运行。在LogAct中，智能体动作在执行前即会在共享日志中可见；可通过可插拔的解耦投票器在执行前被终止；并在智能体或环境发生故障时实现一致性恢复。LogAct支持智能体内省机制，使智能体能够利用大语言模型推理分析自身执行历史，进而实现语义级别的恢复、健康检查与优化。实验评估表明，LogAct智能体能够高效准确地从故障中恢复、调试自身性能、优化群体中的令牌使用，并在代表性基准测试中仅牺牲3%的正常功能性能即可完全阻止目标模型执行所有非预期动作。