LLM

This post summarizes LightMem: Lightweight and Efficient Memory-Augmented Generation. The easiest way to give an LLM agent memory of past conversation is to stuff the whole history back into the prompt every time. That approach falls apart as conversations grow. A long context triggers the “Lost in the Middle” problem, where information buried in the middle gets ignored, and memory systems that re-read the accumulated history on every turn pay for it with higher compute and slower responses. LightMem targets both problems at once. It’s a lightweight memory-generation system that cuts token usage to a fraction of what existing systems need, while outperforming them. ...

This post summarizes the Microsoft Research paper From Local to Global: A GraphRAG Approach to Query-Focused Summarization, drawing also on the video [Paper Review] GraphRAG by Seoul National University’s DSBA Lab. RAG works by building a trusted document collection ahead of time, then, when a question comes in, retrieving the relevant documents and handing them to an LLM as grounding for its answer. The basic pieces are indexing (chunking documents into a searchable form), retrieval (finding documents relevant to the question), and generation (producing an answer from the retrieved documents and the question). ...