paper-with-me

Papers

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

2026-03-08 · Zongqian Li, Tengchao Lv, Shaohan Huang, Yixuan Su, Qinzheng Sun, Qiufeng Yin, Ying Xin, Scarlett Li, Lei Cui, Nigel Collier, Furu Wei arxiv

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing and difficulty scaling. We introduce a four-stage Data Processing Framework encompassing collection, processing, filtering, and verification, incorporating Automatic Difficulty Filtering via an LLM-based predict-calibrate-select framework that leverages multi-dimensional difficulty metrics across five weighted dimensions to retain challenging problems while removing simplistic ones. The resulting MicroCoder dataset comprises tens of thousands of curated real competitive programming problems from diverse platforms, emphasizing recency and difficulty. Evaluations on strictly unseen LiveCodeBench demonstrate that MicroCoder achieves 3x larger performance gains within 300 training steps compared to widely-used baseline datasets of comparable size, with consistent advantages under both GRPO and its variant training algorithms. The MicroCoder dataset delivers obvious improvements on medium and hard problems across different model sizes, achieving up to 17.2% relative gains in overall performance where model capabilities are most stretched. These results validate that difficulty-aware data curation improves model performance on challenging tasks, providing multiple insights for dataset creation in code generation.

📄 PDF Abstract BibTeX arXiv:2603.07779

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningCode Generation

Similar Papers 제목 키워드 기반

PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation

2025-09-23 · Alexandre Piché, Ehsan Kamalloo, Rafael Pardinas, Xiaoyin Chen 외 arxiv

Reinforcement Learning (RL) is increasingly utilized to enhance the reasoning capabilities of Large Language Models (LLMs). However, effectively scaling these RL methods presents significant challenges, primarily due to …

Reinforcement Learning

LLMs Encode How Difficult Problems Are

2025-10-20 · William Lugoloobi, Chris Russell arxiv

Large language models exhibit a puzzling inconsistency: they solve complex problems yet frequently fail on seemingly simpler ones. We investigate whether LLMs internally encode problem difficulty in a way that aligns wit…

Reinforcement Learning

Select and Improve: Understanding the Mechanics of Post-Training for Reasoning

2026-06-11 · Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman arxiv

Reinforcement learning has rapidly emerged as a key component in the training of reasoning and coding models, yet it remains poorly understood from a mechanistic perspective. We study how and through what underlying proc…

Reinforcement Learning

TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL

2026-06-01 · Tianze Yang, Yucheng Shi, Ruitong Sun, Jingyuan Huang 외 arxiv

Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets, with fixed image-question-answer samples…

Reinforcement LearningMultimodal ReasoningVisual Reasoning

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

2026-06-12 · Ge Wang, Xinyu Tan, Xiang Li, Man Luo 외 arxiv

Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigidity ignores the uneven difficulty of rob…

Reinforcement LearningRobot Manipulation