14 papers
MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning
Meng Lu, Yuxing Lu, Yuchen Zhuang +6
Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning t…
DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization
Xuan Xie, Xuan Wang, Wenjie Wang +2
The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy…
DeepEvidence: Empowering Biomedical Discovery with Deep Knowledge Graph Research
Zifeng Wang, Zheng Chen, Ziwei Yang +5
Biomedical knowledge graphs (KGs) encode vast, heterogeneous information spanning literature, genes, pathways, drugs, diseases, and clinical trials, but leveraging them collectivel…
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
Meng Lu, Ran Xu, Yi Fang +14
While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, rem…
LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology
Sajib Acharjee Dip, Adrika Zafor, Bikash Kumar Paul +4
Large language models (LLMs) and emerging agentic frameworks are beginning to transform single-cell biology by enabling natural-language reasoning, generative annotation, and multi…
JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation
Zhenyu Bi, Gaurav Srivastava, Yang Li +4
While small language models (SLMs) have shown promise on various reasoning tasks, their ability to judge the correctness of answers remains unclear compared to large language model…