5 papers
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6
Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…
CocoaBench: Evaluating Unified Digital Agents in the Wild
CocoaBench Team, Shibo Hao, Zhining Zhang +29
LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly int…
World Reasoning Arena
PAN Team, Qiyue Gao, Kun Zhou +15
World models (WMs) are intended to serve as internal simulators of the real world that enable agents to understand, anticipate, and act upon complex environments. Existing WM bench…
Math Natural Language Inference: this should be easy!
Valeria de Paiva, Qiyue Gao, Hai Hu +4
We ask whether contemporary LLMs are able to perform natural language inference (NLI) tasks on mathematical texts. We call this the Math NLI problem. We construct a corpus of Math…
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation
Qiyue Gao, Xinyu Pi, Kevin Liu +21
Internal world models (WMs) enable agents to understand the world's state and predict transitions, serving as the basis for advanced deliberative reasoning. Recent large Vision-Lan…