PseudoAct: 通过伪代码合成实现大型语言模型代理的灵活规划与动作控制
PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents
AI总结:
PseudoAct通过伪代码合成实现LLM代理的灵活规划与动作控制,提升长时决策效率。
摘要:
大型语言模型(LLM)代理通常依赖于反应式决策范式,如ReAct,根据不断增长的执行历史选择动作。尽管在短任务中有效,这些方法在涉及分支、迭代或多工具协调的复杂长时间跨度任务中往往导致工具使用冗余、推理不稳定和高token消耗。为了解决这些限制,本文介绍了一种新的框架PseudoAct,通过伪代码合成实现LLM代理的灵活规划和动作控制。利用LLM表达任务解决策略的能力,PseudoAct合成一个结构化的伪代码计划,将任务分解为子任务,并显式编码控制流,包括顺序、条件语句、循环、并行组合以及这些逻辑原语的组合。然后通过遵循此全局计划执行动作,使决策逻辑显式且时间上一致。该设计减少了冗余动作,防止无限循环,避免无信息的替代探索,使决策过程一致且高效。在基准数据集上的实验表明,我们的方法显著优于现有的反应式代理方法,在FEVER上成功率达到20.93%的绝对提升,并在HotpotQA上设定了新的最先进的水平。
英文摘要:
Large language model (LLM) agents typically rely on reactive decision-making paradigms such as ReAct, selecting actions conditioned on growing execution histories. While effective for short tasks, these approaches often lead to redundant tool usage, unstable reasoning, and high token consumption in complex long-horizon tasks involving branching, iteration, or multi-tool coordination. To address these limitations, this paper introduces PseudoAct, a novel framework for flexible planning and action control in LLM agents through pseudocode synthesis. Leveraging the ability of LLMs to express task-solving strategies as code, PseudoAct synthesizes a structured pseudocode plan that decomposes a task into subtasks and explicitly encodes control flow, including sequencing, conditionals, loops, parallel composition, and combinations of these logic primitives. Actions are then executed by following this global plan, making the decision logic explicit and temporally coherent. This design reduces redundant actions, prevents infinite loops, and avoids uninformative alternative exploration, enabling consistent and efficient long-horizon decision-making. Experiments on benchmark datasets show that our method significantly outperforms existing reactive agent approaches, achieving a 20.93% absolute gain in success rate on FEVER and setting a new state-of-the-art on HotpotQA.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。