# Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning

arXiv: https://arxiv.org/abs/2409.12452 · HTML: https://mlsanity.com/paper/2409.12452/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 62 of its 74 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 62)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)

## Built on by (most cited first, 25 of 25)

- [Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing](https://mlsanity.com/paper/2506.09965/) (2025)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [ARM: Adaptive Reasoning Model](https://mlsanity.com/paper/2505.20258/) (2025)
- [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025)
- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [a1: Steep Test-time Scaling Law via Environment Augmented Generation](https://mlsanity.com/paper/2504.14597/) (2025)
- [CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs](https://mlsanity.com/paper/2507.03254/) (2025)
- [Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals](https://mlsanity.com/paper/2505.18071/) (2025)
- [Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code](https://mlsanity.com/paper/2508.08322/) (2025)
- [Towards Verified Code Reasoning by LLMs](https://mlsanity.com/paper/2509.26546/) (2025)
- [Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism](https://mlsanity.com/paper/2510.13170/) (2025)
- [Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment](https://mlsanity.com/paper/2506.00845/) (2025)
- [RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library](https://mlsanity.com/paper/2504.20426/) (2025)
- [KG-Augmented Executable CoT for Mathematical Coding](https://mlsanity.com/paper/2508.04072/) (2025)
- [DynaAct: Large Language Model Reasoning with Dynamic Action Spaces](https://mlsanity.com/paper/2511.08043/) (2025)
- [Contract-Coding: Towards Repo-Level Generation via Structured Symbolic Paradigm](https://mlsanity.com/paper/2604.13100/) (2026)
- [A Multi-Agent Framework for Stateful Inference-Time Search](https://mlsanity.com/paper/2510.07147/) (2025)
- [Neurosymbolic Language Reasoning as Satisfiability Modulo Theory](https://mlsanity.com/paper/2602.18095/) (2026)
- [Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought](https://mlsanity.com/paper/2603.18334/) (2026)
- [Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching](https://mlsanity.com/paper/2605.08658/) (2026)
- [Visual Compliance via Executable Safety Rule Entailment](https://mlsanity.com/paper/2609.18328/) (2026)
- [Marathoner: Ultra-Long-Horizon Autonomous Intelligence](https://mlsanity.com/paper/2609.34378/) (2026)
- [Representation-Aligned Auxiliary Supervision for Language Model Adaptation](https://mlsanity.com/paper/2610.04098/) (2026)

## Abstract (arXiv)

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly rely on prompting or task-specific fine-tuning, often suffering from poor robustness and cross-task generalization. To address the limitation, we introduce CodePlan, a scalable framework that empowers LLMs to generate and follow textitcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. By leveraging the structured and versatile nature of code, CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. Importantly, CodePlan allows automatic extraction of code-form plans from massive, wide-ranging text corpora without the need for curated, task-specific datasets. This enables it to scale up efficiently and improve LLM's reasoning capabilities across diverse scenarios. To train CodePlan, we construct a large-scale dataset of 2M examples that integrate code-form plans with standard prompt-response pairs from existing corpora. With minimal computation overhead during both training and inference, CodePlan achieves a 25.1% relative improvement compared with directly generating responses, averaged across 13 challenging multi-step reasoning benchmarks, spanning mathematical reasoning, symbolic reasoning, instruction-following, multi-hop QA, and decision-making tasks. Further analysis reveals CodePlan's increasing performance gains on more complex reasoning tasks, as well as significant data efficiency thanks to its generalization ability.