9 papers · 1 filter
Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems
Zongqian Li, Tengchao Lv, Shaohan Huang +8
Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We…
Code Aesthetics with Agentic Reward Feedback
Bang Xiao, Lingjie Jiang, Shaohan Huang +5
Large Language Models (LLMs) have become valuable assistants for developers in code-related tasks. While LLMs excel at traditional programming tasks such as code generation and bug…
Geometric-Mean Policy Optimization
Yuzhong Zhao, Yue Liu, Junpeng Liu +9
Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unf…
Information-Preserving Reformulation of Reasoning Traces for Antidistillation
Jiayu Ding, Lei Cui, Li Dong +2
Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex tasks. While revealing these reason…
LongReasonArena: A Long Reasoning Benchmark for Large Language Models
Jiayu Ding, Shuming Ma, Lei Cui +2
Existing long-context benchmarks for Large Language Models (LLMs) focus on evaluating comprehension of long inputs, while overlooking the evaluation of long reasoning abilities. To…
Think Only When You Need with Large Hybrid-Reasoning Models
Lingjie Jiang, Xun Wu, Shaohan Huang +7
Recent Large Reasoning Models (LRMs) have shown substantially improved reasoning capabilities over traditional Large Language Models (LLMs) by incorporating extended thinking proce…