HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published 4 days ago • 238
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 19 days ago • 340
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Paper • 2608.16072 • Published 19 days ago • 151
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published 26 days ago • 342
TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting Paper • 2607.28261 • Published Jul 30 • 116
stefanocarrera/sqlautophagycode_D_test_Qwen3-8B_t1.25_g5_run0_metrics Viewer • Updated Jul 20 • 579 • 16 • 1
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 212
EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos Paper • 2607.09701 • Published Jun 21 • 17
timaeus/rl-lm-pythia1b-sentiment-neg-alpha0-grpo-nostd-gs4-tp1-tk0-pt80000-lr1e-6-bs600-seed1 Updated Jul 16 • 1