Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization
Ru Wang, Wei Huang, Selena Song +5
Generalization to novel compound tasks under distribution shift is important for deploying transformer-based language models (LMs). This work investigates Chain-of-Thought (CoT) re…
cs.CL2026
Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
Ru Wang, Wei Huang, Qi Cao +3
Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable…