10 papers
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin +8
Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is…
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Yang Liu, Enxi Wang, Yufei Gao +6
Despite the success of reinforcement learning for large language models, a common failure mode is reduced sampling diversity, where the policy repeatedly generates similar erroneou…
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining
Zhiyuan Zeng, Yichi Zhang, Yong Shan +11
While Large Language Models (LLMs) have achieved remarkable success in code generation, they often struggle with the deep, long-horizon reasoning required for complex software engi…
ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models
Zhangyue Yin, Qiushi Sun, Zhiyuan Zeng +4
Test-time scaling has emerged as a transformative paradigm for enhancing the performance of large reasoning models, enabling dynamic allocation of computational resources during in…
FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen +28
Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncert…
Dynamic and Generalizable Process Reward Modeling
Zhangyue Yin, Qiushi Sun, Zhiyuan Zeng +3
Process Reward Models (PRMs) are crucial for guiding Large Language Models (LLMs) in complex scenarios by providing dense reward signals. However, existing PRMs primarily rely on h…