#論文

Agent memory is just lookup: reading arXiv:2604.27707 with CTX and OCR-Memory in mind

The paper argues that RAG, vector stores, and scratchpads are retrieval, not learning. Read alongside CTX and OCR-Memory, the gap between 'better search' and 'weight-level learning' becomes concrete.

Human-LLM text segmentation on M1 Max: WCP works, raw log-likelihood doesn't

Tested arXiv:2605.03723 on M1 Max + Qwen3-8B-Base: WCP runs in pure Python, but raw log-likelihood floods boundaries even on human-only text.

OCR-Memory Lets Agents Recall History as Images

A read of arXiv:2604.26622 OCR-Memory. It renders agent execution history into images, uses Set-of-Mark to let a VLM pick relevant segments, then retrieves verbatim text from the original logs.