Metraipolis › archive › dc_caeee79bdebe

TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue — arXiv:2611.02001

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02001
License (as archived): CC0-1.0
Archived: 2026-11-03T10:36:20.271Z
SHA-256 of the archived text: fca3ee84b77a8340ab52844ad8f3aa484219332369d012cd105fdaa587153c49
Stable URL of this page: https://metraipolis.com/documento/dc_caeee79bdebe

How to cite

TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue — arXiv:2611.02001 — arXiv (en), https://arxiv.org/abs/2611.02001 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_caeee79bdebe (Metraipolis archive dc_caeee79bdebe, sha256 fca3ee84b77a8340ab52844ad8f3aa484219332369d012cd105fdaa587153c49)

BibTeX

@misc{dccaeee79bdebe,
  title = {TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue — arXiv:2611.02001},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02001},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_caeee79bdebe; sha256 fca3ee84b77a8340ab52844ad8f3aa484219332369d012cd105fdaa587153c49},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02001. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which something was said. Financial dialogue breaks this assumption: figures are revised, stances shift without being restated, rules stated once govern later questions, and a single company is discussed under several analytical lenses. Memory systems that retrieve the passages most similar to a question, or the most recent ones, therefore return superseded values, miss rules that share no wording with the question, and cannot recover a stance spread across sessions. We present TrackMem, a per-speaker graph memory that tracks the history of figures, separates perspectives by entity and lens, and preserves each speaker's actions in chronological order. To evaluate it, we introduce FinLoCoMo, a benchmark of 15 long-horizon investment conversations with 765 questions in two splits: one following the LoCoMo categories and one targeting four failure modes. With two readers, TrackMem outperforms existing memory systems on both splits. On the failure-mode split it reaches 73.9% macro accuracy against 69.4% for the strongest baseline, with the largest gains on questions about revised figures (86.5% against 73.4%).

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/2611.02001 — 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 2026-11-03T10:29:48.832Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).