ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds Paper • 2609.30199 • Published Sep 24 • 27
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration Paper • 2605.03042 • Published May 4 • 157
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company Paper • 2604.22446 • Published Apr 24 • 102
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 Sentence Similarity • 0.1B • Updated Jan 28 • 27.8M • • 1.5k
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Paper • 2604.11297 • Published Apr 13 • 144
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 249
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Paper • 2603.25730 • Published Mar 26 • 39