AI Papers - 2026-10-19

DailyArxiv - AI Research Podcast · Oct 19, 2026 · 14m

Today's papers: - Towards Continual Learning: Mitigating Forgetting With Subspace Tuning: https://arxiv.org/abs/2610.22293v1 - Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries: https://arxiv.org/abs/2610.22273v1 - Progress Reward Model for Reinforcement Learning via Large Language Models: https://arxiv.org/abs/2610.22056v1 - Dexterity from Supervised Play: https://arxiv.org/abs/2610.22340v1 - Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond: https://arxiv.org/abs/2610.21539v1 This podcast is from Colin Davis…