PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents
#Large Language Models #PseudoAct #ReAct #pseudocode synthesis #control flow #FEVER #HotpotQA #tool coordination #long‑horizon tasks #benchmark performance
📌 Key Takeaways
- Proposal of PseudoAct, a pseudocode‑based planning framework for LLM agents.
- Explicitly encodes control flow (sequence, conditionals, loops, parallelism).
- Reduces redundant tool usage, prevents infinite loops, and limits uninformative exploration.
- Achieves a 20.93% absolute improvement on FEVER and sets new state‑of‑the‑art on HotpotQA.
- Published on arXiv (cs.AI, eess.SY) on 27 Feb 2026 by authors Yihan Wen and Xin Chen.
📖 Full Retelling
Yihan Wen and Xin Chen introduced the PseudoAct framework on arXiv (submission 27 Feb 2026) to enhance flexible planning and action control in large language model agents. By synthesizing structured pseudocode that encodes control flow—sequences, conditionals, loops, and parallel composition—they aim to overcome the redundant tool usage and unstable reasoning that plague reactive paradigms such as ReAct in complex, long‑horizon tasks. Experimental results demonstrate a 20.93 % absolute gain on the FEVER benchmark and a new state‑of‑the‑art performance on HotpotQA, highlighting the framework’s effectiveness for coherent, efficient decision‑making.
🏷️ Themes
Large Language Model Agents, Pseudocode Synthesis, Planning and Control, Reactive Decision‑Making, Benchmark Evaluation
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
--> Computer Science > Artificial Intelligence arXiv:2602.23668 [Submitted on 27 Feb 2026] Title: PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents Authors: Yihan Wen, Xin Chen View a PDF of the paper titled PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents, by Yihan Wen and 1 other authors View PDF HTML Abstract: Large language model 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. Subjects: Artificial Intelligence (cs.AI) ; Systems and Control (eess.SY) Cite as: arXiv:2602.23668 [cs.AI] (or arXiv:2602.23668v1 [cs.AI] for this version) https://doi.org/10.4855...
Read full article at source