Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation Paper • 2610.21601 • Published Oct 15 • 36
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics Paper • 2609.35259 • Published Sep 28 • 33
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published Sep 22 • 33
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published Sep 14 • 143
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published Sep 3 • 77
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published Sep 17 • 209
ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement Paper • 2610.06347 • Published Oct 5 • 5
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published Sep 21 • 164
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback Paper • 2608.30241 • Published Aug 31 • 13
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability Paper • 2608.30320 • Published Aug 31 • 62
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning Paper • 2608.09888 • Published Aug 10 • 747
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 110
Towards Automating Scientific Review with Google's Paper Assistant Tool Paper • 2606.28277 • Published Jun 26 • 11
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards Paper • 2605.10899 • Published May 11 • 54
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published Jun 1 • 96