LLM agent 的有界自糾錯長期記憶層：將連續、含矛盾的專案互動日誌精煉成有界、可自更新的記憶庫。Bounded, self-correcting long-term memory for LLM agents — candidate
LLM agent 的有界自糾錯長期記憶層：將連續、含矛盾的專案互動日誌精煉成有界、可自更新的記憶庫。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay evals.
你是這個專案的維護者嗎？展示它已收錄於 YunoDB。
[](https://yunodb.com/tools/1173591564dynamics-memory?utm_source=github&utm_medium=badge)<a href="https://yunodb.com/tools/1173591564dynamics-memory?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/1173591564dynamics-memory.svg" alt="Featured on YunoDB" height="20"></a>
