Metraipolis › archive › dc_a76fedd812e6

Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows — arXiv:2610.03564

Source
arXiv
Original
https://arxiv.org/abs/2610.03564
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:42.563Z
SHA-256 of the archived text
a0e6c23a464b4162477840d35c216cb3bb29a0b5ef95b72f3891fd8a7c129a5f
Stable URL of this page
https://metraipolis.com/documento/dc_a76fedd812e6

How to cite

Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows — arXiv:2610.03564 — arXiv, https://arxiv.org/abs/2610.03564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a76fedd812e6 (Metraipolis archive dc_a76fedd812e6, sha256 a0e6c23a464b4162477840d35c216cb3bb29a0b5ef95b72f3891fd8a7c129a5f)
BibTeX
@misc{dca76fedd812e6,
  title = {Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows — arXiv:2610.03564},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03564},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a76fedd812e6; sha256 a0e6c23a464b4162477840d35c216cb3bb29a0b5ef95b72f3891fd8a7c129a5f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Financial AI agents must do more than retrieve facts: investment workflows require correct quantitative execution, reliable use of procedural resources, and auditable structured outputs. We introduce FinSkillBench, an evaluation suite of 2,603 point in time episodes across 12 subtasks in portfolio construction, risk management, and fundamental analysis, with hidden regenerable ground truth and task specific deterministic verifiers. Executing 17,820 episodes across 9 models and 3 resource conditions, the paired analysis across 8 models shows that curated skill packages raise mean scores by +16.2 points (0.366 to 0.528), whereas skills generated within a single episode add only +0.5 points while consuming more tokens and turns. We then decompose the curated premium by granting human authored procedural documents and executable domain tools separately: documents alone add +5.6 points, tools alone add +19.5 points, and their combination is subadditive. The premium is strongly workflow dependent: executable tools dominate numerically intensive workflows, documentation matters more when procedural or output schema guidance is the bottleneck, and interpretive tasks benefit from both. The effects are sign stable across 10 scoring variants and cluster bootstrap analyses, and an independently implemented second harness reproduces the directional pattern while showing that effect magnitudes depend on how tools and data are exposed. Overall, a measured "skill premium" is a property of the full model, resource, and harness system rather than of the underlying model alone.

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/2610.03564 — 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 2026-10-05T22:45:55.706Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).