Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published 4 days ago • 132
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Paper • 2608.25593 • Published 4 days ago • 107
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published 4 days ago • 170
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 13 days ago • 339
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published 5 days ago • 135
EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published 10 days ago • 270
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist Paper • 2608.13558 • Published 17 days ago • 91
Demystifying Agent Skills: Why They Work-Until They Don't Paper • 2608.14036 • Published 16 days ago • 169
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Paper • 2608.16072 • Published 13 days ago • 150
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization Paper • 2608.09043 • Published 20 days ago • 8
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published 20 days ago • 342
Recursive Synthesis for Long-Horizon Terminal Tasks Paper • 2608.05466 • Published 23 days ago • 249
TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting Paper • 2607.28261 • Published about 1 month ago • 116
Running on Zero MCP 130 ImageGen 🖼 130 Multi-task image generator with dynamic, chainable workflows
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published about 1 month ago • 309
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation Paper • 2607.26811 • Published Jul 29 • 93