Lanxiang Hu

lmgame-Bench: How Good are LLMs at Playing Games?

Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs

AR Models can be Faster and More Accurate Parallel Decoders than Diffusion LLMs

GameArena: Evaluating LLM Reasoning through Live Computer Games

Scaling Long Context Training Data by Long-Distance Referrals