16 papers
When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
Wendi Yu, Lianhao Zhou, Xiangjue Dong +6
LLM powered multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, their advantages over single-agent systems (SAS) remain unclear, with perform…
FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time
Montgomery Bohde, Hongxuan Liu, Mrunali Manjrekar +4
Tandem mass spectrometry is prominent in scientific discovery workflows for identifying unknown small molecules, yet high-throughput structural elucidation remains challenging. Whi…
ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents
Zhuofeng Li, Yi Lu, Dongfu Jiang +7
The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate s…
Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
Lianhao Zhou, Hongyi Ling, Cong Fu +14
Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous sys…
Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency
Yuchao Lin, Jacob Helwig, Shurui Gui +1
We consider achieving equivariance in machine learning systems via frame averaging. Current frame averaging methods involve a costly sum over large frames or rely on sampling-based…
Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
Shubham Parashar, Shurui Gui, Xiner Li +8
We aim to improve the reasoning capabilities of language models via reinforcement learning (RL). Recent RL post-trained models like DeepSeek-R1 have demonstrated reasoning abilitie…