5 papers
TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT
Rana Muhammad Shahroz Khan, Zijie Liu, Zhen Tan +2
Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) are the two dominant paradigms for enhancing Large Language Model (LLM) performance on downstream tasks. While RL gener…
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…
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…
A Layered Protocol Architecture for the Internet of Agents
Charles Fleming, Luca Muscariello, Vijoy Pandey +1
Large Language Models (LLMs) have demonstrated remarkable performance improvements and the ability to learn domain-specific languages (DSLs), including APIs and tool interfaces. Th…
Command-V: Pasting LLM Behaviors via Activation Profiles
Barry Wang, Avi Schwarzschild, Alexander Robey +4
Retrofitting large language models (LLMs) with new behaviors typically requires full finetuning or distillation-costly steps that must be repeated for every architecture. In this w…