한국어 Oct 01, 2026 [논문 리뷰] HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents Sep 28, 2026 [논문 리뷰] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Sep 17, 2026 [논문 리뷰] DAPO: Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization Aug 03, 2026 [논문 리뷰] Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Jul 31, 2026 [논문 리뷰] Kimi K3: Open Frontier Intelligence Jun 29, 2026 [논문 리뷰] Autodata: An agentic data scientist to create high quality synthetic data May 29, 2026 [논문 리뷰] Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents English Oct 01, 2026 [Paper Review] HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents Sep 28, 2026 [Paper Review] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Sep 17, 2026 [Paper Review] DAPO: Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization Aug 03, 2026 [Paper Review] Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Jul 31, 2026 [Paper Review] Kimi K3: Open Frontier Intelligence Jun 29, 2026 [Paper Review] Autodata: An agentic data scientist to create high quality synthetic data May 29, 2026 [Paper Review] Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents