Prover-Verifier Games improve legibility of LLM outputs(arxiv.org)42 points by jonbaer 2 years ago | 3 comments
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents(arxiv.org)184 points by geuds 2 years ago | 91 comments
GPUDrive: Data-driven, multi-agent driving simulation at 1M FPS(arxiv.org)90 points by jonbaer 2 years ago | 9 comments
StructuredRAG: JSON Response Formatting with Large Language Models(arxiv.org)23 points by bobvanluijt 2 years ago | 3 comments