4 papers
Selm: Self-Evolving Library Management for Multi-Skill Agent Optimization
Mengxi Hu, Yuxuan Hu, Jinbo Su +6
Large language model (LLM) agents increasingly use skills as a lightweight way to acquire task-specific knowledge. Recent work enables skills to evolve from task trajectories. Howe…
GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
Weixian Waylon Li, Jiaxin Zhang, Han Zhou +4
Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipel…
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
Sijia Luo, Xiaokang Zhang, Yuxuan Hu +6
Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing K…
SAM Decoding: Speculative Decoding via Suffix Automaton
Yuxuan Hu, Ke Wang, Xiaokang Zhang +4
Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have y…