NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 5 days ago • 407
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published 12 days ago • 267
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 27 days ago • 340
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill Paper • 2608.11924 • Published Aug 12 • 291
KKHYA/llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-4of8-impinit-lr5e-4-sd3_20260812_063335 Text Generation • 4B • Updated Aug 12 • 21 • 1
Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs Paper • 2608.01755 • Published Aug 3 • 142
dRAE: Representation Autoencoder with Hyper-Spherical Codes Paper • 2607.22148 • Published Jul 24 • 12
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey Paper • 2607.21655 • Published Jul 22 • 193
makermods/act_makermods_sock_2_orange_color_only_2026-07-20_17-08-14 Robotics • 51.7M • Updated Jul 20 • 8 • 1
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 213