# Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling

arXiv: https://arxiv.org/abs/2412.15305 · HTML: https://mlsanity.com/paper/2412.15305/

## Key facts

- Cited by 11 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 28 of its 45 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [Chain of Code: Reasoning with a Language Model-Augmented Code Emulator](https://mlsanity.com/paper/2312.04474/) (2023)
- [Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives](https://mlsanity.com/paper/2401.02009/) (2024)
- [L2MAC: Large Language Model Automatic Computer for Extensive Code Generation](https://mlsanity.com/paper/2310.02003/) (2023)
- [LeTI: Learning to Generate from Textual Interactions](https://mlsanity.com/paper/2305.10314/) (2023)
- [Learning Task Decomposition to Assist Humans in Competitive Programming](https://mlsanity.com/paper/2406.04604/) (2024)
- [SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation](https://mlsanity.com/paper/2411.11053/) (2024)
- [JumpCoder: Go Beyond Autoregressive Coder via Online Modification](https://mlsanity.com/paper/2401.07870/) (2024)

## Built on by (most cited first, 11 of 11)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging](https://mlsanity.com/paper/2508.18993/) (2025)
- [RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving](https://mlsanity.com/paper/2505.21577/) (2025)
- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search](https://mlsanity.com/paper/2509.25420/) (2025)
- [Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models](https://mlsanity.com/paper/2512.20677/) (2025)
- [Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding](https://mlsanity.com/paper/2508.17971/) (2025)
- [TheoremForge: Scaling up Formal Data Synthesis with Low-Budget Agentic Workflow](https://mlsanity.com/paper/2601.17332/) (2026)
- [Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation](https://mlsanity.com/paper/2510.19868/) (2025)
- [LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software](https://mlsanity.com/paper/2604.12994/) (2026)

## Abstract (arXiv)

Solving complex reasoning tasks is a key real-world application of agents. Thanks to the pretraining of Large Language Models (LLMs) on code data, recent approaches like CodeAct successfully use code as LLM agents' action, achieving good results. However, CodeAct greedily generates the next action's code block by relying on fragmented thoughts, resulting in inconsistency and instability. Moreover, CodeAct lacks action-related ground-truth (GT), making its supervision signals and termination conditions questionable in multi-turn interactions. To address these issues, we first introduce a simple yet effective end-to-end code generation paradigm, CodeProgram, which leverages code's systematic logic to align with global reasoning and enable cohesive problem-solving. Then, we propose Tree-of-Code (ToC), which self-grows CodeProgram nodes based on the executable nature of the code and enables self-supervision in a GT-free scenario. Experimental results on two datasets using ten popular zero-shot LLMs show ToC remarkably boosts accuracy by nearly 20% over CodeAct with less than 1/4 turns. Several LLMs even perform better on one-turn CodeProgram than on multi-turn CodeAct. To further investigate the trade-off between efficacy and efficiency, we test different ToC tree sizes and exploration mechanisms. We also highlight the potential of ToC's end-to-end data generation for supervised and reinforced fine-tuning.