Wen-Feng Feng

Gating policy distillation with directional agreement between early and late RL shifts unlocks more effective knowledge transfer, boosting LLM performance on reasoning tasks.

Broader tokenizer alignment in on-policy distillation can actively harm performance by introducing noisy supervision signals.

Past post-training successes often turn toxic when reapplied to drifted checkpoints, making pre-training experience authorization essential to prevent autonomous self-improvement loops from wasting compute and destabilizing model weights.

Stop relying on stochasticity: this work shows how distilling experience into hierarchical knowledge unlocks more effective and stable LLM-based agentic search.