Search

huggingface.co › papers › 2605.06716

Paper page - From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

Papers arxiv:2605.06716 From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms Published on May 7 Submitted by Hongzhan Lin on May 11 Authors: , , , , , , , , Abstract Large language model agents rely on memory mechanisms that evolve through three stages—storage, refle… …

May 11, 2026

huggingface.co › papers › 2606.09707

Paper page - BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

… By abstracting storage formats and memory management, BrainSurgery executes complex transformations through declarative YAML plans . …

Jun 10, 2026

huggingface.co › blog › ggml-org

New in llama.cpp: Model Management

… This is good addition, Thank you. what is the best way to get and the tokens in between? openAI library is removing them.. i want to run llama-server in console and talk to it using a python library that does not remove the thinking tokens. i checked the llama-cpp-python but it does not have that. … …

Dec 11, 2025