The paper introduces MemGPT, a system that uses virtual context management to extend the limited context windows of large language models (LLMs), enabling tasks like document analysis and extended conversations. MemGPT is evaluated in document analysis and multi-session chat, showing improved performance. Code and data are released at https://memgpt.ai.

https://arxiv.org/abs//2310.08560

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers