Jun Song

The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.

SafeSteer proposes a localized on-policy distillation method that restricts safety alignment to specific safety tokens, thereby achieving strong safety performance with minimal degradation to general capabilities and significantly reducing data requirements.

This paper introduces Test-Time Harness Evolution (TTHE), a method for optimizing LLM agent harnesses during evaluation using execution traces, without requiring gold labels or training.