TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
Electronics and Telecommunications Research Institute(电信研究所);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);Hugging Face;Ant Group(蚂蚁集团)
Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul, Jiasi Shen, Jing Tang, Jianguo Li
备注:
The first three authors contributed equally to this work; listing order is random
Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is essential to overcoming this hurdle. Reinforcement Fine-Tuning (RFT) has emerged as a promising strategy to address this need. However, most existing approaches overlook the heterogeneous difficulty and granularity inherent in test cases, leading to an imbalanced distribution of reward signals and consequently biased gradient updates during training. To address this, we propose Test-driven and cApability-adaptive cuRriculum reinfOrcement fine-Tuning (TAROT). TAROT systematically constructs, for each problem, a four-tier test suite (basic, intermediate, complex, edge), providing a controlled difficulty landscape for curriculum design and evaluation. Crucially, TAROT decouples curriculum progression from raw reward scores, enabling capability-conditioned evaluation and principled selection from a portfolio of curriculum policies rather than incidental test-case difficulty composition. This design fosters stable optimization and more efficient competency acquisition. Extensive experimental results reveal that the optimal curriculum for RFT in code generation is closely tied to a model's inherent capability, with less capable models achieving greater gains with an easy-to-hard progression, whereas more competent models excel under a hard-first curriculum. TAROT provides a reproducible method that adaptively tailors curriculum design to a model's capability, thereby consistently improving the functional correctness and robustness of the generated code. All code and data are released to foster reproducibility and advance community research at https://github.com/deep-diver/TAROT.
KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);State Key Laboratory of AI Safety(人工智能安全国家重点实验室);School of Computer Science, University of Chinese Academy of Sciences(中国科学院大学计算机科学学院)
Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning
School of Information, Renmin University of China(中国人民大学信息学院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学歌华人工智能学院);Alibaba Group(阿里巴巴集团)
AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation
East China Normal University(东华师范大学);Hasso Plattner Institute/University of Potsdam(哈索·platzer研究所/波茨坦大学);Tongji University(同济大学);Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室)
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Tencent AI Seattle Lab(腾讯AI西雅图实验室);Washington University in St. Louis(华盛顿大学圣路易斯分校);University of Maryland, College Park(马里兰大学科廷分校);The University of Texas at Dallas(德克萨斯大学达拉斯分校)
Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Tsinghua University(清华大学);WeChat, Tencent(微信、腾讯);Department of Data Science, City University of Hong Kong(香港城市大学数据科学系)
Probing the Difficulty Perception Mechanism of Large Language Models
Institute of Digital Twin, EIT(数字孪生研究所,EIT);Wuhan University of Science and Technology(武汉科技大学);Zhejiang University(浙江大学);Hong Kong Polytechnic University(香港理工大学);Shenzhen Institutes of Advanced Technology, CAS(深圳先进技术研究院,中国科学院)
OpenLearnLM Benchmark: A Unified Framework for Evaluating Knowledge, Skill, and Attitude in Educational Large Language Models
Chosun University(chosun大学);Korea University(韩国大学);Ewha Womans University(成均馆大学);Korea Institute for Curriculum and Evaluation(韩国课程评价院);Seoul National University(首尔国立大学);Texas A&M University(德克萨斯农工大学);Indiana University Bloomington(印第安纳大学布卢明顿分校)