Microsoft Research has introduced PlugMem, a task-agnostic long-term memory module that can be attached to any large language model agent and reportedly cuts context token usage by 10 to 100 times without requiring fine-tuning. The work was detailed in a paper titled "PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents" (arXiv:2603.03296) and elaborated in an official Microsoft Research blog post, with code and experimental results released on GitHub.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.