Yuxuan Cai

S KILL G YM : I NTERNALIZING L ARGE -S CALE H UMAN S KILLS INTO LLM S FOR R EAL -W ORLD P ROBLEM S OLVING

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

35B \texttt{SkillGym-Agent} reaches 51.47\% on skill-assisted SkillsBench, exceeding reported scores for Claude Sonnet 4.6, GPT-5.4 Mini, and DeepSeek V4 Pro, suggesting reusable procedural competence.

AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search

This work proposes \textsc{AutoMem}, a text-gradient recursive self-improvement framework for task-adaptive memory architecture search that consistently discovers task-adaptive memory architectures that outperform the strongest human-designed memory baselines.

ContextWeave: A Real-World Workflow Benchmark

ContextWeave is introduced, a longitudinal benchmark that evaluates whether recalled experience improves downstream agent performance in realistic office-work streams and motivates memory systems that optimize not only retrieval relevance but also reliable use during execution.