SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries Paper • 2608.05604 • Published 10 days ago • 74
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 15 days ago • 252
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution Paper • 2608.07645 • Published 9 days ago • 26
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization Paper • 2608.08156 • Published 8 days ago • 9
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models Paper • 2608.03457 • Published 12 days ago • 32
CAPEval: A Decoupled Caption Evaluation across Understanding and Generation Paper • 2608.02589 • Published 13 days ago • 25
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 13 days ago • 155
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF Image-Text-to-Text • 9B • Updated 3 days ago • 639k • 391
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Paper • 2607.28568 • Published 17 days ago • 183