HarnessEvolve：從參考軌跡學習，實現可靠的代理自我演化
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
arXiv
1
Liang-Hsun Huang 許願
Agent Seer：從規格理解合成評測情境
Agent Seer: Synthesizing Scenarios from Specification Understanding
arXiv
25
Liang-Hsun Huang 許願
深入 Claude Code：當代與未來 AI 智能體系統的設計空間
Dive into Claude Code The Design Space of Todays and Future AI Agent Systems
arXiv
195
Teds Lin 許願