德州大学 Jev-Mem 让 AI 记忆构建提速 6.6 倍
德州大学Jev-Mem让AI记忆构建提速6.6倍
德州大学论文提出 Jev-Mem，将链接、停止搜索等小决策交给快速打分模型 Jev 批量输出概率，LLM 只在最后读取记忆并作答，使长对话记忆构建速度提升 6.6 倍。在 LoCoMo 长对话基准上，其回答得分 0.777，高于最佳基线的 0.700；记忆构建耗时 158 秒，最快对手为 1,044 秒，回答耗时 0.93 秒对 1.47 秒。
Rohan Paul· @rohanpaul_ai · X·2026-10-25 22:27· 51 分钟前AI 评分42
AI 导读
德州大学论文提出Jev-Mem，把链接、停止搜索等小决策交给快速打分模型Jev批量输出概率，LLM只在最后读取记忆并作答，使长对话记忆构建速度提升6.6倍。在LoCoMo长对话基准上，其回答得分0.777，高于最佳基线的0.700；记忆构建耗时158秒，最快对手为1,044秒，回答耗时0.93秒对1.47秒。
正文 · 原文
University of Texas paper finds that handing small memory decisions to a fast scoring model let an AI memory system build its memory of long conversations 6.6 times faster
Many memory systems ask an LLM to make small choices, like what to link or when to stop searching.
Generating text for each choice is slow, and those calls pile up during memory building and search.
Jev-Mem gives those choices to a fast scorer, Jev, that returns probabilities in batches instead of text. The LLM is called only at the end, to read the chosen memories and answer.
On the LoCoMo long-conversation benchmark, it got a 0.777 answer score versus 0.700 for the best baseline. It built memory in 158 seconds versus 1,044 for the fastest rival and answered in 0.93 seconds versus 1.47.
If your memory pipeline calls an LLM for routing, scoring, or stopping, try a fast classifier there and save the LLM for answers.
来源：Rohan Paul · x.com
来源：RadarAI · aihot.news