activity
20242026
collaborators

11 papers

cs.AI2026

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

Yuhang Zhou, Kai Zheng, Haoling Li +3

On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. H…

cs.AI2026

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

Haoling Li, Kai Zheng, Jie Wu +4

Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reli…

cs.LG2026

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

Haipeng Luo, Qingfeng Sun, Songli Wu +4

Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from poli…

cs.AI2026

RubricBench: Aligning Model-Generated Rubrics with Human Standards

Qiyuan Zhang, Junyi Zhou, Yufei Wang +8

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided ev…

cs.AI2026

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models

Qiyuan Zhang, Yufei Wang, Tianhe Wu +5

Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evalua…

cs.AI2026

AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent

Haipeng Luo, Huawen Feng, Qingfeng Sun +6

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and strug…