HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published Sep 1 • 250
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published Aug 26 • 60
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published Aug 17 • 122
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published Aug 25 • 139
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 180
OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models Paper • 2607.23193 • Published Jul 28 • 8