# TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation

arXiv: https://arxiv.org/abs/2511.22277 · HTML: https://mlsanity.com/paper/2511.22277/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://mlsanity.com/paper/2010.12884/) (2020)
- [If beam search is the answer, what was the question?](https://mlsanity.com/paper/2010.02650/) (2020)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models](https://mlsanity.com/paper/2309.02772/) (2023)
- [CRANE: Reasoning with constrained LLM generation](https://mlsanity.com/paper/2502.09061/) (2025)
- [IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking](https://mlsanity.com/paper/2410.07295/) (2024)
- [Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective](https://mlsanity.com/paper/2506.05754/) (2025)
- [KV Cache Compression for Inference Efficiency in LLMs: A Review](https://mlsanity.com/paper/2508.06297/) (2025)
- [Controllable Generation via Locally Constrained Resampling](https://mlsanity.com/paper/2410.13111/) (2024)
- [When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)](https://mlsanity.com/paper/1809.00069/) (2018)
- [Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access](https://mlsanity.com/paper/2401.09967/) (2024)
- [Enhancing SQL Query Generation with Neurosymbolic Reasoning](https://mlsanity.com/paper/2408.13888/) (2024)
- [A Systematic Literature Review on Neural Code Translation](https://mlsanity.com/paper/2505.07425/) (2025)

## Built on by (most cited first, 5 of 5)

- [Learning Adaptive LLM Decoding](https://mlsanity.com/paper/2603.09065/) (2026)
- [Verifier-Guided Code Translation via Meta-Step Decoding](https://mlsanity.com/paper/2605.17626/) (2026)
- [Diagnosing CFG Interpretation in LLMs](https://mlsanity.com/paper/2604.20811/) (2026)
- [Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code](https://mlsanity.com/paper/2607.13921/) (2026)
- [Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code](https://mlsanity.com/paper/2608.22652/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and flexible framework to date for exploring decoding strategies, constraints, and hyperparameters in LLMs, and use it in code generation to enforce correctness and structure during decoding rather than relying on prompt engineering. TreeCoder represents decoding as a tree search over candidate programs, where both decoding strategies and constraint functions - such as style, syntax, execution - are treated as first-class, optimisable components. This design enables systematic exploration and automatic tuning of decoding configurations using standard optimisation techniques. Experiments on the MBPP (Python) and SQL-Spider benchmarks show that TreeCoder consistently improves accuracy across open-source models such as CodeLlama, Mistral and DeepSeek, often outperforming their unconstrained baselines by considerable margins.