Metraipolis › archive › dc_cd2a14fcb06f

TEM: Temporal State Tracking Memory for Large Language Model Agents — arXiv:2610.21900

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.21900
License (as archived): CC0-1.0
Archived: 2026-10-16T10:01:56.152Z
SHA-256 of the archived text: 464e4589e386bf3b51961147b38ed55084eea2527523e959633e5c078973211a
Stable URL of this page: https://metraipolis.com/documento/dc_cd2a14fcb06f

How to cite

TEM: Temporal State Tracking Memory for Large Language Model Agents — arXiv:2610.21900 — arXiv (en), https://arxiv.org/abs/2610.21900 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd2a14fcb06f (Metraipolis archive dc_cd2a14fcb06f, sha256 464e4589e386bf3b51961147b38ed55084eea2527523e959633e5c078973211a)

BibTeX

@misc{dccd2a14fcb06f,
  title = {TEM: Temporal State Tracking Memory for Large Language Model Agents — arXiv:2610.21900},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21900},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd2a14fcb06f; sha256 464e4589e386bf3b51961147b38ed55084eea2527523e959633e5c078973211a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21900. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An agent's memory must remain useful as information changes across conversations. A new fact may replace an earlier value without making that value irrelevant to a later question. We present Temporal State Tracking Memory (TEM), a training-free framework for tracking these changes. TEM stores facts as versioned records linked to their sources. It retrieves relevant versions, places them in source order and labels historical records before passing the evidence to the answer model. Event memory and original dialogue turns provide details missing from structured facts. We evaluated TEM on 420 questions drawn from 600 sessions involving 60 personas. Across four open-weight models, key-entity hit rates reached 75.71-97.62% overall and 96.67-100.00% on the historical-residence subset. Adding historical labels to otherwise identical, source-ordered facts increased overall hit rates by 17.14-55.95 percentage points. The evidence was compact: 94-118 tokens per answer, or 48.75-56.73% less than session-aware retrieval-augmented generation (RAG). A further evaluation on 1,540 LoCoMo questions tested hybrid memory under a fixed evidence budget. TEM exceeded session-aware RAG with both backbones; conservative score differences were 7.92 and 10.58 percentage points. The results support preserving fact versions and exposing their temporal status to the generator when answering questions about repeatedly updated information.

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/2610.21900 — 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 2026-10-16T08:44:47.680Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).