view article Article Introducing A5: Proactive Personal Agent in Your Life-Long Context KYLN24 • 5 days ago • 22
Teaching a Moving Student: Rethinking the Curriculum of On-Policy Distillation Paper • 2609.25048 • Published Sep 26 • 1
When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents Paper • 2608.05810 • Published Sep 17 • 1
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training Paper • 2602.22576 • Published Feb 26 • 4
Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA Paper • 2602.22584 • Published Feb 26 • 5
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents Paper • 2602.14257 • Published Feb 15 • 4
Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents Paper • 2411.06559 • Published Nov 10, 2024 • 16
Balancing Pipeline Parallelism with Vocabulary Parallelism Paper • 2411.05288 • Published Nov 8, 2024 • 20