# ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation

arXiv: https://arxiv.org/abs/2609.34717 · HTML: https://mlsanity.com/paper/2609.34717/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (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)
- [RLTF: Reinforcement Learning from Unit Test Feedback](https://mlsanity.com/paper/2307.04349/) (2023)
- [S*: Test Time Scaling for Code Generation](https://mlsanity.com/paper/2502.14382/) (2025)
- [Coder Reviewer Reranking for Code Generation](https://mlsanity.com/paper/2211.16490/) (2022)
- [Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback](https://mlsanity.com/paper/2403.16792/) (2024)
- [RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation](https://mlsanity.com/paper/2409.09584/) (2024)
- [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://mlsanity.com/paper/2510.06186/) (2025)
- [CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment](https://mlsanity.com/paper/2510.18471/) (2025)
- [LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops](https://mlsanity.com/paper/2603.23613/) (2026)
- [An Iterative Test-and-Repair Framework for Competitive Code Generation](https://mlsanity.com/paper/2604.05560/) (2026)

## Abstract (arXiv)

Open-weight large language models (LLMs) can generate function-level programs from natural-language prompts, but plausible candidates still fail on hidden semantics and repeat mistakes across repair attempts. We present ReMCTS, an execution-grounded, memory-augmented, LLM-guided MCTS-style search framework. It organizes program candidates as tree states, retains branch-local debugging context, retrieves failure experience across branches, and distinguishes failed checks from unavailable evidence. On HumanEval and MBPP-Sanitized, visible-test ReMCTS improves over direct generation in 8 of 10 model-dataset pairs under held-out evaluation, whereas proxy-only search is less stable. Controlled tree-search, sampling, repair, and memory ablations characterize the source and limits of these gains. A 30-task HumanEval-X C++ pilot further demonstrates compatibility with compiler-backed execution, but does not constitute a broad multilingual evaluation.