7 papers
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
Xinyi He, Qian Liu, Mingzhe Du +6
Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impres…
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Zhenghai Xue, Longtao Zheng, Qian Liu +4
Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However…
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
Weihao Zeng, Yuzhen Huang, Qian Liu +4
DeepSeek-R1 has shown that long chain-of-thought (CoT) reasoning can naturally emerge through a simple reinforcement learning (RL) framework with rule-based rewards, where the trai…
First Return, Entropy-Eliciting Explore
Tianyu Zheng, Tianshun Xing, Qingshui Gu +10
Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (…
ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention
Yuhong Chou, Zehao Liu, Ruijie Zhu +6
Linear attention mechanisms deliver significant advantages for Large Language Models (LLMs) by providing linear computational complexity, enabling efficient processing of ultra-lon…
General-Reasoner: Advancing LLM Reasoning Across All Domains
Xueguang Ma, Qian Liu, Dongfu Jiang +3
Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforceme…