Metraipolis › archive › dc_8701cfd8273a
TransMem: Transition-Aware Retrieval for Evolving Personal Memory — arXiv:2611.10683
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10683
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:29.404Z
- SHA-256 of the archived text
4c47ad31b95acc6803e12990ee36d11b0962d6ea64a628c50c53b845a2ec9e11- Stable URL of this page
https://metraipolis.com/documento/dc_8701cfd8273a
How to cite
TransMem: Transition-Aware Retrieval for Evolving Personal Memory — arXiv:2611.10683 — arXiv (en), https://arxiv.org/abs/2611.10683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8701cfd8273a (Metraipolis archive dc_8701cfd8273a, sha256 4c47ad31b95acc6803e12990ee36d11b0962d6ea64a628c50c53b845a2ec9e11)
BibTeX
@misc{dc8701cfd8273a,
title = {TransMem: Transition-Aware Retrieval for Evolving Personal Memory — arXiv:2611.10683},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10683},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8701cfd8273a; sha256 4c47ad31b95acc6803e12990ee36d11b0962d6ea64a628c50c53b845a2ec9e11},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term personalized agents are increasingly expected to answer queries over user histories in which preferences, goals, and constraints evolve across interleaved conversations. Existing retrieval-based and structured-memory systems can surface relevant facts, but often return isolated memory units that do not explain which earlier preference was refined, contradicted, or superseded by later evidence. We introduce TransMem, a transition-aware memory retrieval framework that stores preference updates as explicit retrieval units alongside ordinary factual memories. During memory construction, TransMem routes user interaction history into topic-structured memory graphs, detects shift events, and grounds them as transition records. At inference time, TransMem first retrieves factual anchors and then adaptively expands over transition records, producing a compact context of factual anchors and accepted transition records. Experiments on PersonaMem and PersonaBench across two Qwen backbones show that TransMem outperforms representative retrieval-based and structured-memory baselines. Controlled analyses further show that transition records and adaptive expansion contribute beyond factual anchoring, chronological expansion, flat transition retrieval, and fixed-hop traversal. These results suggest that preference-update records are useful retrieval units for long-term personalization. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.10683 — 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 2026-11-10T18:37:52.427Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).