3 papers
cs.AI2026
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
Jie-Jing Shao, Haiyan Yin, Yueming Lyu +5
Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mit…
cs.LG2026
Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm
Wen-Da Wei, Han-Bin Fang, Yang-Di Liu +3
Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate activations for backpropagation…
cs.CL2024
Direct Alignment of Language Models via Quality-Aware Self-Refinement
Runsheng Yu, Yong Wang, Xiaoqi Jiao +2
Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternat…