Persistent Memory for Language Models

Persistent memory lets language models carry useful information across conversations, tasks, or long sequences without repeatedly processing the full history. Approaches include extracting and compressing facts or episodes for lexical, vector, and graph-based retrieval; managing memory through updates, provenance, and forgetting; and adding learned latent, parametric, recurrent, or persistent key-value states. Systems are commonly tested on cross-session question answering and personalization benchmarks such as LoCoMo and LongMemEval, as well as long-context reasoning and interactive agent tasks. The central tension is retaining enough faithful, current evidence for reliable reasoning while controlling storage, token, and latency costs—and preventing stale, sensitive, or poisoned memories from shaping answers.