SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 10 days ago • 135
What Does Privileged Information Add to On-Policy Self-Distillation? Paper • 2609.20612 • Published 10 days ago • 36
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 10 days ago • 183