# PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization

arXiv: https://arxiv.org/abs/2506.01475 · HTML: https://mlsanity.com/paper/2506.01475/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [Iterative Reasoning Preference Optimization](https://mlsanity.com/paper/2404.19733/) (2024)
- [AgentGym: Evolving Large Language Model-based Agents across Diverse Environments](https://mlsanity.com/paper/2406.04151/) (2024)
- [BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents](https://mlsanity.com/paper/2308.05960/) (2023)
- [AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System](https://mlsanity.com/paper/2402.15538/) (2024)
- [AgentRefine: Enhancing Agent Generalization through Refinement Tuning](https://mlsanity.com/paper/2501.01702/) (2025)
- [Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents](https://mlsanity.com/paper/2402.11651/) (2024)
- [Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents](https://mlsanity.com/paper/2402.00798/) (2024)
- [LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner](https://mlsanity.com/paper/2409.20560/) (2024)

## Built on by (most cited first, 8 of 8)

- [ReCode: Unify Plan and Action for Universal Granularity Control](https://mlsanity.com/paper/2510.23564/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [A2Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators](https://mlsanity.com/paper/2511.20693/) (2025)
- [PABU: Progress-Aware Belief Update for Efficient LLM Agents](https://mlsanity.com/paper/2602.09138/) (2026)
- [Retrospective Progress-Aware Self-Refinement for LLM Agent Training](https://mlsanity.com/paper/2606.14302/) (2026)
- [Healthcare AI GYM for Medical Agents](https://mlsanity.com/paper/2605.02943/) (2026)
- [ParaCook: On Time-Efficient Planning for Multi-Agent Systems](https://mlsanity.com/paper/2510.11608/) (2025)
- [Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models](https://mlsanity.com/paper/2603.13985/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to guide reasoning, which is verbose and inefficient. NL plans are also tailored to specific tasks and restrict agents' ability to generalize across similar tasks. To this end, we explore pseudocode-style plans (P-code Plan) to capture the structural logic of reasoning. We find that P-code Plan empowers LLM agents with stronger generalization ability and more efficiency. Inspired by this finding, we propose a pseudocode-style Planning Guided Preference Optimization method called PGPO for effective agent learning. With two planning-oriented rewards, PGPO further enhances LLM agents' ability to generate high-quality P-code Plans and subsequent reasoning. Experiments show that PGPO achieves superior performance on representative agent benchmarks and outperforms the current leading baselines. Analyses reveal the advantage of PGPO in reducing action errors and omissions during reasoning.