
AceCoder
The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis"
Stars: 74

AceCoder is a tool that introduces a fully automated pipeline for synthesizing large-scale reliable tests used for reward model training and reinforcement learning in the coding scenario. It curates datasets, trains reward models, and performs RL training to improve coding abilities of language models. The tool aims to unlock the potential of RL training for code generation models and push the boundaries of LLM's coding abilities.
README:
Authors: Huaye Zeng, Dongfu Jiang, HaoZhe Wang, Ping Nie, Xiaotong Chen, Wenhu Chen @ TIGER-Lab Â
- [2025/2/3] We release the AceCoder Paper, along with the 🤗 Models and Datasets on Hugging Face.
Abstract
-
We introduce AceCoder, the first work to propose a fully automated pipeline for synthesizing large-scale reliable tests used for the reward model training and reinforcement learning in the coding scenario. To do this, we curated the dataset AceCode-87K, where we start from a seed code dataset and prompt powerful LLMs to "imagine" proper test cases for the coding question and filter the noisy ones.
-
We trained two reward model AceCodeRM-7B and AceCodeRM-32B on the constructed preference pairs. Best-of-N sampling results on HumanEval(+), MBPP(+), BigCodeBench, LiveCodeBench (V4) show consistent improvement.
-
We perform RL training from three policy models: Qwen2.5-7B-Instruct and Qwen2.5-Coder-7B-Base and Qwen2.5-Coder-7B-Instruct. Two types of reward can be used, i.e. the trained reward model RM-7B and the rule-based reward, i.e. binary pass rate over the test cases in dataset. Additionaly, we also experiment with RL from the base model like DeepSeek-R1. Results show that directly RL from the Base Qwen2.5-Coder model can get 25% improvement on HumanEval-plus and 6% on MBPP-plus within just 80 optimization steps.
-
To our knowledge, this is the first work to propose a fully automated pipeline for synthesizing large-scale reliable tests used for the reward model training and reinforcement learning in the coding scenario. We believe our \dataset{} will unlock the potential of RL training for code generation models and help the community to further push the boundaries of LLM's coding abilities.
- AceCode-87K: The first large-scale coding dataset with an average of 16 test cases per prompt, synthesized by GPT-4o-mini
- AceCodePair-300K: Constructed preference pairs from AceCode-87K for training reward model.
- AceCode-87K-hard: where you can create sample 25% of the hard examples following commands here
- AceCodeRM-7B: A reward model trained on AceCodePair-300K from Qwen2.5-Coder-7B-Instruct
- AceCodeRM-32B: A reward model trained on AceCodePair-300K from Qwen2.5-Coder-32B-Instruct
Initial Policy Model | Reward Type | Training dataset | Final RL Model |
---|---|---|---|
Qwen2.5-7B-Instruct | AceCodeRM-7B | AceCode-87K-hard (22k) | TIGER-Lab/AceCoder-Qwen2.5-7B-Ins-RM |
Qwen2.5-7B-Instruct | Rule | AceCode-87K-hard (22k) | TIGER-Lab/AceCoder-Qwen2.5-7B-Ins-Rule |
Qwen2.5-Coder-7B-Instruct | AceCodeRM-7B | AceCode-87K-hard (22k) | TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Ins-RM |
Qwen2.5-Coder-7B-Instruct | Rule | AceCode-87K-hard (22k) | TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Ins-Rule |
Qwen2.5-Coder-7B | AceCodeRM-7B | AceCode-87K-hard (22k) | TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Base-RM |
Qwen2.5-Coder-7B | Rule | AceCode-87K-hard (22k) | TIGER-Lab/AceCoder-Qwen2.5-Coder-7B-Base-Rule |
See our website or paper for detailed performance report.
git submodule init
git submodule update
First install acecoder as a package:
pip install https://github.com/TIGER-AI-Lab/AceCoder.git
Then see examples/run_acecoderm.py for how to use AceCoderRM. Quick command python examples/run_acecoderm.py
will run the example.
See train/train_rm/README.md for detailed instructions.
See train/train_rl/README.md for detailed instructions.
We use Evalplus, bigcodebench, LiveCodeBench for evaluation of HumanEval(+), MBPP(+), BigCodeBench, LiveCodeBench (V4) respectively.
If you find this work helpful, please consider citing:
@article{AceCoder,
title={AceCoder: Acing Coder RL via Automated Test-Case Synthesis},
author={Zeng, Huaye and Jiang, Dongfu and Wang, Haozhe and Nie, Ping and Chen, Xiaotong and Chen, Wenhu},
journal={ArXiv},
year={2025},
volume={2502.01718}
}
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for AceCoder
Similar Open Source Tools

AceCoder
AceCoder is a tool that introduces a fully automated pipeline for synthesizing large-scale reliable tests used for reward model training and reinforcement learning in the coding scenario. It curates datasets, trains reward models, and performs RL training to improve coding abilities of language models. The tool aims to unlock the potential of RL training for code generation models and push the boundaries of LLM's coding abilities.

ERNIE
ERNIE 4.5 is a family of large-scale multimodal models with 10 distinct variants, including Mixture-of-Experts (MoE) models with 47B and 3B active parameters. The models feature a novel heterogeneous modality structure supporting parameter sharing across modalities while allowing dedicated parameters for each individual modality. Trained with optimal efficiency using PaddlePaddle deep learning framework, ERNIE 4.5 models achieve state-of-the-art performance across text and multimodal benchmarks, enhancing multimodal understanding without compromising performance on text-related tasks. The open-source development toolkits for ERNIE 4.5 offer industrial-grade capabilities, resource-efficient training and inference workflows, and multi-hardware compatibility.

VILA
VILA is a family of open Vision Language Models optimized for efficient video understanding and multi-image understanding. It includes models like NVILA, LongVILA, VILA-M3, VILA-U, and VILA-1.5, each offering specific features and capabilities. The project focuses on efficiency, accuracy, and performance in various tasks related to video, image, and language understanding and generation. VILA models are designed to be deployable on diverse NVIDIA GPUs and support long-context video understanding, medical applications, and multi-modal design.

FlagEmbedding
FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: * **Long-Context LLM** : Activation Beacon * **Fine-tuning of LM** : LM-Cocktail * **Embedding Model** : Visualized-BGE, BGE-M3, LLM Embedder, BGE Embedding * **Reranker Model** : llm rerankers, BGE Reranker * **Benchmark** : C-MTEB

chronos-forecasting
Chronos is a family of pretrained time series forecasting models based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.

agents-towards-production
Agents Towards Production is an open-source playbook for building production-ready GenAI agents that scale from prototype to enterprise. Tutorials cover stateful workflows, vector memory, real-time web search APIs, Docker deployment, FastAPI endpoints, security guardrails, GPU scaling, browser automation, fine-tuning, multi-agent coordination, observability, evaluation, and UI development.

EmbodiedScan
EmbodiedScan is a holistic multi-modal 3D perception suite designed for embodied AI. It introduces a multi-modal, ego-centric 3D perception dataset and benchmark for holistic 3D scene understanding. The dataset includes over 5k scans with 1M ego-centric RGB-D views, 1M language prompts, 160k 3D-oriented boxes spanning 760 categories, and dense semantic occupancy with 80 common categories. The suite includes a baseline framework named Embodied Perceptron, capable of processing multi-modal inputs for 3D perception tasks and language-grounded tasks.

MiniCPM-V
MiniCPM-V is a series of end-side multimodal LLMs designed for vision-language understanding. The models take image and text inputs to provide high-quality text outputs. The series includes models like MiniCPM-Llama3-V 2.5 with 8B parameters surpassing proprietary models, and MiniCPM-V 2.0, a lighter model with 2B parameters. The models support over 30 languages, efficient deployment on end-side devices, and have strong OCR capabilities. They achieve state-of-the-art performance on various benchmarks and prevent hallucinations in text generation. The models can process high-resolution images efficiently and support multilingual capabilities.

inference
Xorbits Inference (Xinference) is a powerful and versatile library designed to serve language, speech recognition, and multimodal models. With Xorbits Inference, you can effortlessly deploy and serve your or state-of-the-art built-in models using just a single command. Whether you are a researcher, developer, or data scientist, Xorbits Inference empowers you to unleash the full potential of cutting-edge AI models.

Awesome-Attention-Heads
Awesome-Attention-Heads is a platform providing the latest research on Attention Heads, focusing on enhancing understanding of Transformer structure for model interpretability. It explores attention mechanisms for behavior, inference, and analysis, alongside feed-forward networks for knowledge storage. The repository aims to support researchers studying LLM interpretability and hallucination by offering cutting-edge information on Attention Head Mining.

AIGC_text_detector
AIGC_text_detector is a repository containing the official codes for the paper 'Multiscale Positive-Unlabeled Detection of AI-Generated Texts'. It includes detector models for both English and Chinese texts, along with stronger detectors developed with enhanced training strategies. The repository provides links to download the detector models, datasets, and necessary preprocessing tools. Users can train RoBERTa and BERT models on the HC3-English dataset using the provided scripts.

rai
RAI is a framework designed to bring general multi-agent system capabilities to robots, enhancing human interactivity, flexibility in problem-solving, and out-of-the-box AI features. It supports multi-modalities, incorporates an advanced database for agent memory, provides ROS 2-oriented tooling, and offers a comprehensive task/mission orchestrator. The framework includes features such as voice interaction, customizable robot identity, camera sensor access, reasoning through ROS logs, and integration with LangChain for AI tools. RAI aims to support various AI vendors, improve human-robot interaction, provide an SDK for developers, and offer a user interface for configuration.

SimAI
SimAI is the industry's first full-stack, high-precision simulator for AI large-scale training. It provides detailed modeling and simulation of the entire LLM training process, encompassing framework, collective communication, network layers, and more. This comprehensive approach offers end-to-end performance data, enabling researchers to analyze training process details, evaluate time consumption of AI tasks under specific conditions, and assess performance gains from various algorithmic optimizations.

uqlm
UQLM is a Python library for Large Language Model (LLM) hallucination detection using state-of-the-art uncertainty quantification techniques. It provides response-level scorers for quantifying uncertainty of LLM outputs, categorized into four main types: Black-Box Scorers, White-Box Scorers, LLM-as-a-Judge Scorers, and Ensemble Scorers. Users can leverage different scorers to assess uncertainty in generated responses, with options for off-the-shelf usage or customization. The library offers illustrative code snippets and detailed information on available scorers for each type, along with example usage for conducting hallucination detection. Additionally, UQLM includes documentation, example notebooks, and associated research for further exploration and understanding.
For similar tasks

AceCoder
AceCoder is a tool that introduces a fully automated pipeline for synthesizing large-scale reliable tests used for reward model training and reinforcement learning in the coding scenario. It curates datasets, trains reward models, and performs RL training to improve coding abilities of language models. The tool aims to unlock the potential of RL training for code generation models and push the boundaries of LLM's coding abilities.

RLHF-Reward-Modeling
This repository contains code for training reward models for Deep Reinforcement Learning-based Reward-modulated Hierarchical Fine-tuning (DRL-based RLHF), Iterative Selection Fine-tuning (Rejection sampling fine-tuning), and iterative Decision Policy Optimization (DPO). The reward models are trained using a Bradley-Terry model based on the Gemma and Mistral language models. The resulting reward models achieve state-of-the-art performance on the RewardBench leaderboard for reward models with base models of up to 13B parameters.

RLHF-Reward-Modeling
This repository, RLHF-Reward-Modeling, is dedicated to training reward models for DRL-based RLHF (PPO), Iterative SFT, and iterative DPO. It provides state-of-the-art performance in reward models with a base model size of up to 13B. The installation instructions involve setting up the environment and aligning the handbook. Dataset preparation requires preprocessing conversations into a standard format. The code can be run with Gemma-2b-it, and evaluation results can be obtained using provided datasets. The to-do list includes various reward models like Bradley-Terry, preference model, regression-based reward model, and multi-objective reward model. The repository is part of iterative rejection sampling fine-tuning and iterative DPO.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.