Executable Code Actions Elicit Better LLM Agents Paper โข 2402.01030 โข Published Feb 1, 2024 โข 97
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper โข 2502.15007 โข Published 20 days ago โข 162
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 Paper โข 2502.03544 โข Published Feb 5 โข 43
Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models Paper โข 2501.13629 โข Published Jan 23 โข 44
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents Paper โข 2407.16741 โข Published Jul 23, 2024 โข 71
MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers Paper โข 2305.07185 โข Published May 12, 2023 โข 9