The authors developed EnSIMem, which processes interaction histories offline into theme-coherent episodes.
Entity-structured indexes help agents retrieve precise long-term memories
EnSIMem organizes dialogue into entity-property records linked to source evidence, then retrieves compact evidence sets for several forms of memory reasoning.
Big Tech
Xuanyu Meng · Xing Fan · Xinyi Fan · Chenlei Guo · Yixuan Xie · Jiawei Han
University of Illinois Urbana-Champaign · Amazon
Research Digest··2 min read
Meng et al.
Why this paper
From Amazon and University of Illinois Urbana-Champaign · Released code
In one line
Entity-structured indexing with episode provenance improves long-term agent memory retrieval and answer accuracy over summary-based systems.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§