Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning

Excerpt

arXiv:2610.02687v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in enterprise, scientific, and medical applications, where agents must incorporate domain-specific knowledge and adapt from experience. Context engineering offers a practical alternative to weight updates by improving model behavior through instructions, strategies, and evidence supplied at inference time. However, adapting context online typically requires a costly trial-and-error pr