Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs Paper • 2605.30501 • Published 8 days ago • 29
Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models Paper • 2602.08658 • Published Feb 9 • 13
Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation Paper • 2602.02007 • Published Feb 2 • 19
When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment Paper • 2509.00544 • Published Aug 30, 2025 • 11