5 papers
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
Zijian Wu, Xiangyan Liu, Xinyuan Zhang +12
MCP standardizes how LLMs interact with external systems, forming the foundation for general agents. However, existing MCP benchmarks remain narrow in scope: they focus on read-hea…
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
Renjie Luo, Zichen Liu, Xiangyan Liu +5
LLMs are often trained with RL from human or AI feedback, yet such methods typically compress nuanced feedback into scalar rewards, discarding much of their richness and inducing s…
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
Zijian Wu, Jinjie Ni, Xiangyan Liu +3
Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively. In this work, w…
Fostering Video Reasoning via Next-Event Prediction
Haonan Wang, Hongfu Liu, Xiangyan Liu +4
Next-token prediction serves as the foundational learning task enabling reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning c…
NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
Xiangyan Liu, Jinjie Ni, Zijian Wu +5
Recent advances in reinforcement learning (RL) have strengthened the reasoning capabilities of vision-language models (VLMs). However, enhancing policy exploration to better scale…