Jonathan Cook

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs

Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents

RACCOON: Regret-based Adaptive Curricula for Cooperation

TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation

Towards Learning to Reason at Pre-Training Scale

Ad-Hoc Human-AI Coordination Challenge

Ad-Hoc Human-AI Coordination Challenge