SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring Paper • 2608.09802 • Published 21 days ago • 133
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published Jul 6 • 48
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning Paper • 2607.07508 • Published Jul 8 • 32
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence Paper • 2606.19348 • Published Apr 26 • 41
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published Jun 11 • 96
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published Jun 11 • 112