3 papers
cs.AI2026
VASP Agent: An Agentic Framework for Autonomous First-principles Calculations
Zeyu Xia, Jinzhe Ma, Congjie Zheng +11
Large Language Models (LLMs) are increasingly embedded in agentic frameworks for scientific discovery. First-principles materials computation imposes a demanding standard for auton…
cs.LG2026
Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving
Chang Su, Zhongkai Hao, Zhizhou Zhang +4
Large language models (LLMs) with reasoning abilities have demonstrated growing promise for tackling complex scientific problems. Yet such tasks are inherently domain-specific, unb…
cs.CL2025
STAIR: Improving Safety Alignment with Introspective Reasoning
Yichi Zhang, Siyuan Zhang, Yao Huang +7
Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods ty…