Metraipolis › archive › dc_fc4fc3817a24

CosmosAlpha: Multi-Relational Graph Search with Pareto-Guided Exploration for LLM-Driven Alpha Mining — arXiv:2611.04555

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04555
License (as archived)
CC0-1.0
Archived
2026-11-04T21:40:05.469Z
SHA-256 of the archived text
94cb564951b95f9230e696af1370ea81da88088e6388ca0c617c56a66bc0178a
Stable URL of this page
https://metraipolis.com/documento/dc_fc4fc3817a24

How to cite

CosmosAlpha: Multi-Relational Graph Search with Pareto-Guided Exploration for LLM-Driven Alpha Mining — arXiv:2611.04555 — arXiv (en), https://arxiv.org/abs/2611.04555 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc4fc3817a24 (Metraipolis archive dc_fc4fc3817a24, sha256 94cb564951b95f9230e696af1370ea81da88088e6388ca0c617c56a66bc0178a)
BibTeX
@misc{dcfc4fc3817a24,
  title = {CosmosAlpha: Multi-Relational Graph Search with Pareto-Guided Exploration for LLM-Driven Alpha Mining — arXiv:2611.04555},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04555},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc4fc3817a24; sha256 94cb564951b95f9230e696af1370ea81da88088e6388ca0c617c56a66bc0178a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04555. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Discovering predictive alpha factors from noisy financial data is a fundamental yet challenging problem in quantitative finance. LLM-driven formulaic alpha mining offers an attractive paradigm by combining interpretable symbolic expressions with iterative generation and refinement guided by quantitative feedback. However, existing generation-centric and tree-based search strategies primarily organize factors through generation lineage, leaving structural and statistical relationships across search branches underutilized. Consequently, information remains localized along parent--child trajectories, which can confine exploration to redundant regions. Moreover, effective factor discovery must account for multiple distinct objectives that cannot be adequately captured by a single search criterion. We introduce CosmosAlpha, a graph-based LLM factor-mining framework that represents discovered factors as a multi-relational graph encoding generation lineage, expression-structure similarity, and cross-sectional exposure correlation. A Graph Flow mechanism propagates search utilities across the graph, allowing each factor to be assessed using relational evidence from nearby factors rather than in isolation. Pareto-guided selection jointly considers quality, fertility and diversity, explicitly modeling their trade-offs within a multi-objective search framework. Across CSI 300 and CSI 500, CosmosAlpha-Graph achieves the best mean rank over seven predictive and portfolio metrics and outperforms its controlled CosmosAlpha-MCTS counterpart on every reported metric, showing a consistent advantage for relational graph search in LLM-driven factor mining. The source code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computational Finance (q-fin.CP) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04555 — 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 2026-11-04T21:35:49.675Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).