The Value of Memory in Language Agents
Resumo indisponível. Consulte o paper original.
PAPER / ARXIV:2610.27043
Joong Ho Choi, Sherine George, Jiayang Zhao, Jayesh Rathi, Ashwin Kandath, Ananya Sane, Vishvak Srinivasan
RESUMO
Financial institutions increasingly deploy large language models (LLMs) in multilingual markets, raising a practical question: can pipelines developed and validated in English be reused across languages, or must they be rebuilt per locale? We test cross-lingual reusability along three dimensions: accuracy, reasoning-effort transfer, and behavioural stability, through three complementary tasks spanning cheque extraction, multilingual QA, and a FinanceBench pilot over SEC 10-K filings in four languages. Accuracy reusability is broadly confirmed, though the language-difficulty ranking reverses between domains. Effort reusability is domain-dependent: higher reasoning effort yields marginal gains on general-knowledge QA but up to 8pp on financial content. Behavioural reusability holds, but per-domain, per-language validation remains necessary -- neither semantic similarity nor self-reported confidence reliably predicts cross-lingual accuracy.
NO MESMO MAPA
Resumo indisponível. Consulte o paper original.
Resumo indisponível. Consulte o paper original.
Resumo indisponível. Consulte o paper original.
Resumo indisponível. Consulte o paper original.
Resumo indisponível. Consulte o paper original.