RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
Read the original on arXiv Computation and Language →RPMem introduces a two‑stage architecture that compiles each session into a model‑independent latent memory and then consolidates it with retained memory via a task‑trained recurrent gate. The consolidated memory is mapped to backbone‑specific low‑rank adaptation (LoRA) parameters, enabling the memory to transfer when the backbone is replaced. Across three long‑term memory benchmarks and five diverse backbones, RPMem achieves broad generalization with near‑constant update cost and memory footprint, outperforming existing parametric and text‑based baselines on the PERMA benchmark.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.