Duyu Tang

HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games

AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints

Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models

Mixture of Lookup Experts

ToolACE: Winning the Points of LLM Function Calling

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

XTransplant: A Probe into the Upper Bound Performance of Multilingual Capability in LLMs via Cross-lingual Transplantation