Zhong-Zhi Li

Beyond Pass@ 1: Self-Play with Variational Problem Synthesis Sustains RLVR

TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning