11 papers
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
Tianqing Fang, Zhisong Zhang, Xiaoyang Wang +16
General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, an…
CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
Zhen Zhang, Kaiqiang Song, Xun Wang +11
AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to su…
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Chengsong Huang, Wenhao Yu, Xiaoyang Wang +6
Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, e…
Enter the Void - Planning to Seek Entropy When Reward is Scarce
Ashish Sundar, Chunbo Luo, Xiaoyang Wang
Model-based reinforcement learning (MBRL) offers an intuitive way to increase the sample efficiency of model-free RL methods by simultaneously training a world model that learns to…
Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies
Siyang Liu, Sahand Sabour, Xiaoyang Wang +1
User studies are central to user experience research, yet recruiting participant is expensive, slow, and limited in diversity. Recent work has explored using Large Language Models…
MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition
Hongzhao Chen, XiaoYang Wang, Jing Lan +9
Automatic speech recognition (ASR) in clinical dialogue demands robustness to full-duplex interaction, speaker overlap, and low-latency constraints, yet open benchmarks remain scar…