MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
As Large Language Models (LLMs) are increasingly used for long-duration tasks, maintaining effective long-term memory has become a critical challenge. Current methods often face a trade-off between cost and accuracy. Simple storage methods often fail to retrieve relevant information, while complex indexing methods (such as memory graphs) require heavy computation and can cause information loss. Furthermore, relying on the working LLM to process all memories is computationally expensive and slow. To address these limitations, we propose MemSifter, a novel framework that offloads the memory retrieval process to a small-scale proxy model. Instead of increasing the burden on the primary worki...
| Authors | Jiejun Tan, Zhicheng Dou, Liancheng Zhang et al. |
|---|---|
| Primary category | cs.IR |
| Published | 3 March 2026 |
| Last updated at source | 21 June 2026 |
Models and datasets referencing this paper
- zstanjj/MemSifter-DatasetsDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.