OmniScientist: An Omni-Modal Omni-Discipline AI Scientist Paper • 2608.13558 • Published 3 days ago • 10
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus Paper • 2608.12149 • Published 4 days ago • 23
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design Paper • 2608.13560 • Published 3 days ago • 38
DarwinX: Evolving Agent Harnesses Through Natural Selection Paper • 2608.07545 • Published 16 days ago • 70
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation Paper • 2608.13489 • Published 3 days ago • 87
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers Paper • 2608.06867 • Published 9 days ago • 97
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Paper • 2608.13546 • Published 3 days ago • 112
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation Paper • 2608.11616 • Published 4 days ago • 6
Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop Paper • 2608.11215 • Published 28 days ago • 5
AVA-Encoder: Towards Agent-Native Video Representation Learning Paper • 2608.12313 • Published 4 days ago • 10
Self-Evolving Embodied Agents via Skill-Harness Evolution Paper • 2608.11350 • Published 5 days ago • 11
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries Paper • 2608.05604 • Published 10 days ago • 74
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design Paper • 2608.10299 • Published 6 days ago • 129
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models Paper • 2608.08627 • Published 7 days ago • 13
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI Paper • 2608.10915 • Published 5 days ago • 188
Business Arena: Benchmarking LLM Agents in a Realistic Marketplace Paper • 2608.08621 • Published 7 days ago • 20