7 papers
SWE-Exp: Experience-Driven Software Issue Resolution
Silin Chen, Shaoxin Lin, Yuling Shi +8
Recent advances in large language model (LLM) agents have shown remarkable progress in software issue resolution, leveraging advanced techniques such as multi-agent collaboration a…
ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
Jianghao Chen, Wei Sun, Qixiang Yin +2
Long-form generation has become a critical and challenging application for Large Language Models (LLMs). Existing studies are limited by their reliance on scarce, high-quality long…
KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning
Wei Sun, Wen Yang, Pu Jian +4
Recent advances have demonstrated that integrating reinforcement learning with rule-based rewards can significantly enhance the reasoning capabilities of large language models, eve…
Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
Pu Jian, Junhong Wu, Wei Sun +3
Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\te…
Latency and Token-Aware Test-Time Compute
Jenny Y. Huang, Mehul Damani, Yousef El-Kurdi +2
Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However,…
An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning
Wei Sun, Qianlong Du, Fuwei Cui +1
Enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) is of great scientific and practical significance. Researchers typically employ process-supervised…