GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills Paper • 2609.21749 • Published 6 days ago • 15
Calibrating Teacher--Student Discrepancy for On-Policy Distillation Paper • 2609.21619 • Published 6 days ago • 13
SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops Paper • 2609.19169 • Published 12 days ago • 6
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence Paper • 2609.05571 • Published 20 days ago • 112
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL Paper • 2609.20715 • Published 7 days ago • 42
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 7 days ago • 172
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure? Paper • 2609.18605 • Published 8 days ago • 40
When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models Paper • 2609.19671 • Published 7 days ago • 48
UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation Paper • 2609.12397 • Published 7 days ago • 43