collaborators

15 papers

cs.AI2026

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

Xujun Li, Kehan Zheng, Mingyuan Zhao +7

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric lea…

cs.CL2026

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Minrui Xu, Zilin Wang, Mengyi DENG +12

Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and…

cs.LG2026

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning

Bowen Ding, Yuhan Chen, Jiayang Lyv +9

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert t…

cs.LG2026

Entropy Centroids as Intrinsic Rewards for Test-Time Scaling

Wenshuo Zhao, Qi Zhu, Xingshan Zeng +4

An effective way to scale up test-time compute of large language models is to sample multiple responses and then select the best one, as in Grok Heavy and Gemini Deep Think. Existi…

cs.CL2026

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study

Zhexin Zhang, Xian Qi Loye, Victor Shea-Jay Huang +8

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do n…

cs.AI2026

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4

Chengwu Liu, Yichun Yin, Ye Yuan +7

Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that simplifies the task relative to what human competitors f…