Metraipolis › archive › dc_fe48c1911286

MemTrial: Learning When to Trust Memory in LLM Portfolio Agents — arXiv:2610.11732

Source

arXiv (en)

Original

https://arxiv.org/abs/2610.11732

License (as archived)

CC0-1.0

Archived

2026-10-09T05:48:22.430Z

SHA-256 of the archived text

7985c8350d6000316794de485c9fdce2ad99b361b299a96ef6264818816badd8

Stable URL of this page

https://metraipolis.com/documento/dc_fe48c1911286

How to cite

MemTrial: Learning When to Trust Memory in LLM Portfolio Agents — arXiv:2610.11732 — arXiv (en), https://arxiv.org/abs/2610.11732 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe48c1911286 (Metraipolis archive dc_fe48c1911286, sha256 7985c8350d6000316794de485c9fdce2ad99b361b299a96ef6264818816badd8)

@misc{dcfe48c1911286,
  title = {MemTrial: Learning When to Trust Memory in LLM Portfolio Agents — arXiv:2610.11732},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11732},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe48c1911286; sha256 7985c8350d6000316794de485c9fdce2ad99b361b299a96ef6264818816badd8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11732. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents for portfolio management learn from experience: they credit each experience in their memory with the outcome of the decisions that used it. In financial markets, however, this outcome mostly reflects the market move shared by all decisions on that date, so the credit tracks the market rather than the experience, and these agents often do worse than simply holding the equal-weight (1/$N$) portfolio. We ask how an agent can credit an experience with what it changes, and answer it by putting memory on trial: drafts of the same decision with and without an experience face the same market, so the outcome they share cancels in their difference. Our agent, MemTrial, drafts each decision with eight combinations of its retrieved experiences, chosen by a fractional factorial design, and credits each experience with its Banzhaf value, the average of these differences. As each date occurs once and each draft is a noisy LLM sample, these credits are noisy and may not hold on new dates. MemTrial therefore pools them across dates and similar experiences with a hierarchical Bayesian model, acts on them only after they have predicted unseen dates, and otherwise stays anchored at a conservative reference such as 1/$N$. On four benchmarks, MemTrial not only benefits from experiences that matter (the best of 15 methods on a semi-synthetic benchmark with known experience quality) but also limits its losses when its values do not hold (at most 2.2\% below 1/$N$ on PortBench and InvestorBench, against 15--38\% for the best experience-learning agent). Averaged over five settings, it improves the utility of the best experience-learning agent by 21.2\%, and with eight LLMs it beats every LLM-based baseline on InvestorBench.

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/2610.11732 — 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 2026-10-09T05:47:00.903Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).