CoT reasoning generalizes via shared predictors in LLMs
CoT generalizes OOD by composing reusable ID transitions with risk bounded by O(k) coefficient.
Stories per day · 30 days
2 RSS
Relatedgeneralization2chain-of-thought1drugood1graph-neural-networks1llm-reasoning1representation-learning1rlvr1
5 stories, newest first · one card per story
Stories tagged #out-of-distribution
RLVR models abandon reasoning strategies under OOD shifts
Co-training with bijective inversion tasks restores derivation and OOD accuracy.
SCARCE learns label-free graph representations robust to distribution shift
A two-stage autoencoder confuses environment signals while preserving reconstruction and leads label-free results on DrugOOD.
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Google Research's RRSI regularizes recursive agent-harness evolution, lifting out-of-distribution scores while cutting policy tokens 30%.
Distance generalization in transformers: why bother with positional encoding?
arXiv study uses synthetic delay-copy tasks to show how RoPE, ALiBi, NoPE and training data diversity affect transformers' distance generalization.