Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Flat cartoon illustration of a cute coral-red lobster mascot character standing centered against a dark charcoal background, holding a glowing white document, with a white speech bubble containing ‘RAG’ in bold sans-serif font, minimalist filing cabinet and floating geometric document icons in the background, clean outlines, kawaii style, high contrast, web interface aesthetic
// Beyond RAG for Agent Memory // RAG wasn’t designed for agent memory. And it shows. The default approach to agent memory today is still the standard RAG pipeline: embed stored memories, retrieve a fixed top-k by similarity, concatenate them into context, and generate an”” https://x.com/dair_ai/status/2018765444702982395
Tuning the chunking phase in RAG systems is notoriously difficult, and the feeling is that there’s no “”optimal”” chunking method. Can it be that different queries just need different chunk sizes, even over the same corpus? (Work by @AI21Labs) >>”” https://x.com/YuvalinTheDeep/status/2018297199025705269
Leave a Reply