Persistent Agent Memory under the EU AI Act and NIS2: Misalignment, Emergent Behaviour and Regulatory Fit
Abstract Agentic AI systems commonly combine a general-purpose AI model with prompts, tools, orchestration and an external memory layer. The model need not be fine-tuned: records retrieved from persistent memory are normally inserted into the model’s inference-time context and can thereby influence later outputs and ac
研究重點
Abstract Agentic AI systems commonly combine a general-purpose AI model with prompts, tools, orchestration and an external memory layer. The model need not be fine-tuned: records retrieved from persistent memory are normally inserted into the model’s inference-time context and can thereby influence later outputs and ac
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
Persistent Agent Memory under the EU AI Act and NIS2: Misalignment, Emergent Behaviour and Regulatory Fit ↗2026-10-12T00:00:00Z · 研究論文索引
延伸探索
相關研究
- Jacobian-Causal Memory Control for Persistent Memory in Language Model Systems相同研究主題 · 2026-11-13
- Neuromodulation-inspired gated associative memory networks: Extended memory retrieval and emergent multistability相同研究主題 · 2026-10-29
- 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