Reproduce “EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Xuanyu Meng, Xing Fan, Xinyi Fan, Chenlei Guo, Yixuan Xie, Jiawei Han

EnSIMem helps assistants answer questions about long conversations by indexing entity–property–value facts and linking them to source turns in topical episodes. At query time, it uses addresses to retrieve original evidence rather than answer from a summary. On LoCoMo, it reaches 90.6% model-judged accuracy, while a fixed-subset ablation scores 96.59% with structured retrieval versus 86.36% dense-only; evaluations cover episodic recall.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.