Metraipolis › archive › dc_e2d4665f530d

AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search — arXiv:2608.11250

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11250
License (as archived)
CC0-1.0
Archived
2026-10-19T05:14:45.572Z
SHA-256 of the archived text
711896c850459446f85e7702fe610d7e57a5033f9c4201bc2fbdeb05c068b73c
Stable URL of this page
https://metraipolis.com/documento/dc_e2d4665f530d

How to cite

AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search — arXiv:2608.11250 — arXiv (en), https://arxiv.org/abs/2608.11250 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2d4665f530d (Metraipolis archive dc_e2d4665f530d, sha256 711896c850459446f85e7702fe610d7e57a5033f9c4201bc2fbdeb05c068b73c)
BibTeX
@misc{dce2d4665f530d,
  title = {AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search — arXiv:2608.11250},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11250},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2d4665f530d; sha256 711896c850459446f85e7702fe610d7e57a5033f9c4201bc2fbdeb05c068b73c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11250. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that searches over frozen research artifacts---hypotheses, executable expressions, platform evidence, rationales, and review status---rather than formulas alone. To our knowledge, AgonAlpha is the first alpha-mining system to combine verified artifact search, a fresh-context adversarial reviewer with re-execution and veto authority, and pending-aware parallel budget allocation, together with a complete public evidence trail. Independent deployments on WorldQuant BRAIN produced SPECTACULAR-grade alphas across five users and six model backends, with Fitness reaching 9.50 and Sharpe reaching 3.48, while retaining prompt-to-expression provenance for every submission.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA); Computational Finance (q-fin.CP); Portfolio Management (q-fin.PM).
Pagina del lavoro: https://arxiv.org/abs/2608.11250 — 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 2026-10-19T05:08:22.836Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).