Metraipolis › archive › dc_bc833f08bfc0

From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory — arXiv:2610.23313

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.23313
License (as archived): CC0-1.0
Archived: 2026-10-19T08:42:34.628Z
SHA-256 of the archived text: d765dfc4fd81248ff7e1fff2fa7e52595801c1590352c509814da5885fe2943f
Stable URL of this page: https://metraipolis.com/documento/dc_bc833f08bfc0

How to cite

From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory — arXiv:2610.23313 — arXiv (en), https://arxiv.org/abs/2610.23313 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc833f08bfc0 (Metraipolis archive dc_bc833f08bfc0, sha256 d765dfc4fd81248ff7e1fff2fa7e52595801c1590352c509814da5885fe2943f)

BibTeX

@misc{dcbc833f08bfc0,
  title = {From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory — arXiv:2610.23313},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23313},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc833f08bfc0; sha256 d765dfc4fd81248ff7e1fff2fa7e52595801c1590352c509814da5885fe2943f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23313. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-term agent memory requires recovering answer-relevant evidence dispersed across turns and sessions. Existing systems increasingly use structured memories and adaptive retrieval, yet often pass retrieved or expanded units directly to the reader, coupling memory addressing with evidence presentation and leaving the final context redundant or incomplete. To address this gap, we propose MemCompile, a query-conditioned evidence compilation framework for long-term conversational memory. Given a query, the Address Plane locates relevant support through compact source-linked descriptors and capacity-aware Cells, while a normalization boundary resolves heterogeneous retrieval hits to stable SourcePacket identities. Its Evidence Plane then allocates a bounded evidence budget across complementary packets, admits limited additional support, and renders the retained claims associated with each selected packet into an answer-ready context. MemCompile achieves 80.52% Judge Accuracy on LoCoMo and extends the empirical quality-cost Pareto frontier to a higher-quality regime. Its strong performance on LongMemEval-S further suggests that the benefits of query-conditioned compilation generalize across long-term conversational-memory benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.23313 — 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 2026-10-19T08:39:10.076Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).