arXiv:2607.07859v1 Announce Type: new Abstract: Reinforcement learning (RL) research has increasingly shifted focus towards alignment, ensuring agents learn behaviors adhering to human values. While human demonstrations and feedback have proven crucial for alignment, existing approaches predominantly combine these signals using multi-stage pipelines designed for the contextual bandit framing of language generation. Yet little work explores how these complementary inputs can serve as a richer, interconnected signal for single-stage offline training in fully sequential decision-making environments. We propose Feedback Manipulation Regularization (FMR), an algorithm-agnostic method that harnesses evaluative feedback as a corrective signal to improve the alignment of imitation learning policies. We adapt Safety Gymnasium environments to be a principled testbed for alignment evaluation, demonstrating improved aptitude and up to a 98% reduction in misalignment across a range of imitation learning algorithms. FMR remains robust in limited data regimes, even when learning from scarce aligned and uninformative noisy demonstrations.
Semantic Drift in LLMs: How Archetypal Attractors (Like “Goblin”) Emerge and How Structured Reflection Reduces Them