Metraipolis › archive › dc_7cb3d30cdb6d

KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory — arXiv:2610.41521

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41521
License (as archived)
CC0-1.0
Archived
2026-11-03T05:45:37.306Z
SHA-256 of the archived text
5e34d39a507b11a91696152a9472796f30bca192ec3f9b442c040b65a7d344ba
Stable URL of this page
https://metraipolis.com/documento/dc_7cb3d30cdb6d

How to cite

KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory — arXiv:2610.41521 — arXiv (en), https://arxiv.org/abs/2610.41521 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cb3d30cdb6d (Metraipolis archive dc_7cb3d30cdb6d, sha256 5e34d39a507b11a91696152a9472796f30bca192ec3f9b442c040b65a7d344ba)
BibTeX
@misc{dc7cb3d30cdb6d,
  title = {KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory — arXiv:2610.41521},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41521},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cb3d30cdb6d; sha256 5e34d39a507b11a91696152a9472796f30bca192ec3f9b442c040b65a7d344ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41521. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many long-term memory systems for LLM agents are built around embedding-based retrieval. Al- though effective for semantic matching, similarity ranking alone does not establish whether re- trieved memories satisfy the conditions implied by a question. In this paper, we introduce KITE (Knowledge-Indexed Temporal Evidence), a vector-free framework that formulates memory re- trieval as an explicit decision procedure. KITE organizes multi-session conversations as structured knowledge indexed by a governed topic vocabulary, which evolves through controlled expansion and consolidation. At query time, questions are compiled into inspectable retrieval plans over the same knowledge index that guides memory construction. The plans are then executed through fixed lookup and ranking operations, while sparse lexical retrieval recovers surface details omitted from the structured representation. Experiments on LoCoMo and LongMemEval-S show that KITE achieves 93.5% and 86.0% accuracy while using only about 1.6k reader-context tokens per ques- tion. These results demonstrate that conversational memory can move beyond similarity ranking by unifying memory construction and query compilation around a governed index, turning retrieval into an inspectable decision procedure for determining which evidence satisfies the question.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.41521 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T05:33:19.066Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).