PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents

TL;DR

PseudoAct introduces pseudocode synthesis for LLM agents, enabling explicit planning and control flow to improve efficiency, stability, and success rates in complex long-horizon tasks.

Contribution

The paper presents PseudoAct, a novel framework that synthesizes pseudocode for structured task planning and control in LLM agents, enhancing performance over reactive methods.

Findings

20.93% success rate improvement on FEVER

State-of-the-art performance on HotpotQA

Reduces redundant actions and prevents infinite loops

Abstract

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.