Kanerva: Token-Budgeted, Validity-Aware Memory for Coding Agents, Without an LLM in the Loop
Coding agents forget everything between sessions, and the memory systems built for them mostly select context by similarity top-k, ignore what items cost in tokens, and have no model of whether a stored fact is still true. We cast agent memory as online budgeted selection, show that the surveyed systems are special cas
研究重點
Coding agents forget everything between sessions, and the memory systems built for them mostly select context by similarity top-k, ignore what items cost in tokens, and have no model of whether a stored fact is still true. We cast agent memory as online budgeted selection, show that the surveyed systems are special cas
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
Kanerva: Token-Budgeted, Validity-Aware Memory for Coding Agents, Without an LLM in the Loop ↗2026-11-01T00:00:00Z · 研究論文索引
延伸探索
相關研究
- Durable Memory on a Fixed Context Budget: Architecture and Measurements of a Long-Lived Coding Agent相同研究主題 · 2026-11-13
- A Collaborative Multiplayer Web IDE and AI Coding Agent with Persistent Project Memory: Architecture, Concurrency Control, and Dual-Tier Knowledge Retention相同研究主題 · 2026-10-16
- VANTAGE-V-AI: Bounded-Memory KV-Cache Compression and Streaming Inference Runtime for Large Language Models相同研究主題 · 2026-11-17