---
id: 20260611-T0-10
title: "研究发现：精简上下文比完整历史更能提升LLM准确性"
title_en: "Lean Context Beats Full History for LLM Accuracy"
url: https://ai.daily.yangsir.net/daily/20260611-T0-10
issue_date: 2026-06-11
publish_date: 2026-06-10T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2606.09900
---

# 研究发现：精简上下文比完整历史更能提升LLM准确性

最新论文提出双时序记忆引擎解决LLM长期记忆问题。传统方法通过回放完整历史来维持记忆，但成本高、速度慢且随干扰增多准确性下降。新实验证明，仅检索关键上下文而非全部历史，能显著提升LLM的准确性和效率。该方法已在arXiv发表，代码开源。

## English Version

**Lean Context Beats Full History for LLM Accuracy**

New research introduces a bi-temporal memory engine addressing LLM long-term memory issues. Traditional approaches replaying full history are costly, slow, and less accurate with increasing distractions. Experiments show that retrieving only key context instead of full history significantly improves LLM accuracy and efficiency. Paper published on arXiv with open-source code.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2606.09900)

**详情页**：https://ai.daily.yangsir.net/daily/20260611-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*