paper / _rockt / May 13 / failedProgramming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
paper / _rockt / May 13 / failedLearning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
paper / _rockt / May 13 / failedDéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems