Qwen-AgentWorld: Language World Models for General Agents(arxiv.org)175 points by ilreb 4 months ago | 47 comments
Orca-Bench: How Ready Are Language Model Agents for Oncall?(arxiv.org)24 points by yruzin 2 months ago | 11 comments
Large Language Models as Optimizers. +50% on Big Bench Hard(arxiv.org)89 points by og_kalu 3 years ago | 32 comments