From Code Completion to Agentic Development: A Survey of AI Coding Agents, Ecosystems, and Evolving Software Engineering Practice
Abstract Large language models have extended software-development assistance from token-level completion to systems that can navigate repositories, edit files, execute tools, and iterate on test feedback. This survey studies the design, use, and evaluation of these AI coding agents, together with their commercial and s
研究重點
Abstract Large language models have extended software-development assistance from token-level completion to systems that can navigate repositories, edit files, execute tools, and iterate on test feedback. This survey studies the design, use, and evaluation of these AI coding agents, together with their commercial and s
為什麼值得關注
這個議題涉及 Crew Pocket、Crew Deck 的實作方向。可先評估現有做法,再決定是否安排小型實驗。
可以進一步驗證什麼?
- 閱讀原文,確認它解決的問題、實驗方法及適用限制
- 檢查相關功能現有做法,找出可比較的差異
- 用小型 PoC 驗證成功率、品質、延遲和實際成本
參考資料
延伸探索
相關研究
- Don’t Trust, Verify: Adaptive Multi-Agent Feature Engineering for Financial Fraud Detection相同研究主題 · 2026-11-16
- From Tool to Agent: How Worker Needs Reorganize Across the Agentic Roles of Workplace AI相同研究主題 · 2026-11-15
- AI Agents and Agentic AI in Medicine: An Autonomy-Centred Scoping Review and Research Agenda相同研究主題 · 2026-11-14