Publications

Decouples exploration from generation at inference time so repeated sampling produces genuinely diverse candidate solutions, improving pass@50 by ~21.6% over standard repeated sampling.

A GRPO-based interactive training method where a teacher model gives corrective feedback on a student model’s rollouts, instilling self-reflective reasoning without distillation.

A diagnostic benchmark spanning eight domains that evaluates LLMs on six dimensions of reasoning about actions and change, including new ramification constraints for indirect effects. State-of-the-art models struggle across all dimensions, especially ramifications.

A contamination-free, time-sensitive QA benchmark built on synthetic facts, forcing models to do genuine temporal reasoning rather than recalling pre-training knowledge.

Systematically constructs contexts that break common assumptions and shows that, while models reason well over assumption-following contexts, performance drops by up to 20% when those assumptions are broken.