Metraipolis › archive › dc_313a7533bc91
Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory — arXiv:2611.02480
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02480
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:58:21.413Z
- SHA-256 of the archived text
def0f141acb2321cc0cd2f52b37c9ba7bcdf6d58fe2612e92abbdffdc3df8fe9- Stable URL of this page
https://metraipolis.com/documento/dc_313a7533bc91
How to cite
Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory — arXiv:2611.02480 — arXiv (en), https://arxiv.org/abs/2611.02480 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_313a7533bc91 (Metraipolis archive dc_313a7533bc91, sha256 def0f141acb2321cc0cd2f52b37c9ba7bcdf6d58fe2612e92abbdffdc3df8fe9)
BibTeX
@misc{dc313a7533bc91,
title = {Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory — arXiv:2611.02480},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02480},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_313a7533bc91; sha256 def0f141acb2321cc0cd2f52b37c9ba7bcdf6d58fe2612e92abbdffdc3df8fe9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02480. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term conversational memory faces a timing mismatch: write-time summaries and graphs organize history before a future query is known, while independent retrieval can allocate a limited evidence budget to redundant or fragmented turns. We introduce Chain on Demand (CoD), a query-time evidence organization framework over an unchanged turn-level memory. Given a broad candidate pool, CoD constructs a temporary evidence chain by allocating a fixed anchor budget according to query relevance, lexical diversity relative to selected anchors, and newly covered query terms, followed by deterministic restoration of each selected anchor's same-session neighborhood. The resulting chain is used only for the current query, while the underlying conversational memory remains unchanged. In a paired comparison over all 1,986 LoCoMo questions, CoD achieves 82.2% accuracy on 1,540 non-adversarial questions and 76.3% on all 1,986 questions. On LongMemEval-S, one fixed configuration that indexes both user and assistant turns obtains 86.6% across all 500 questions. These results show that long-term memory can preserve the original conversation while deferring evidence organization until the information need is known. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.02480 — 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 2026-11-03T10:49:38.650Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).