Metraipolis › archive › dc_ead53c62d5da
From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining — arXiv:2609.35559
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35559
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:58:56.850Z
- SHA-256 of the archived text
511a8176756723d6950e12607312f0b90124ddb396f947e1097f3dd5346c1588- Stable URL of this page
https://metraipolis.com/documento/dc_ead53c62d5da
How to cite
From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining — arXiv:2609.35559 — arXiv (en), https://arxiv.org/abs/2609.35559 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ead53c62d5da (Metraipolis archive dc_ead53c62d5da, sha256 511a8176756723d6950e12607312f0b90124ddb396f947e1097f3dd5346c1588)
BibTeX
@misc{dcead53c62d5da,
title = {From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining — arXiv:2609.35559},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35559},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ead53c62d5da; sha256 511a8176756723d6950e12607312f0b90124ddb396f947e1097f3dd5346c1588},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35559. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Inference scaling has been shown to improve large language model (LLM) performance, and this principle naturally extends to autonomous LLM agents through increased search budgets, which we refer to as *search scaling*. Although prior work has characterized the mechanisms, scaling behavior, and performance limits of LLM inference scaling, much less is known about these questions in autonomous research. Therefore, we investigate how search scaling affects research performance and what mechanisms drive these gains using 50 quantitative factor-mining tasks grounded in financial research reports. Each task requires an agent to carry out an end-to-end research loop, from interpreting a hypothesis and implementing it in code to evaluating and iteratively refining the resulting factor. Across nine models, we examine how model capability, search depth, and search organization shape factor quality by tracing performance across varying budgets, transferring intermediate research states between models, and comparing different search strategies. We find that (1) initial performance is more strongly associated with model capability, while deeper search can narrow cross-model gaps; (2) model grafting shows that the early research state materially shapes final performance; and (3) parallel search outperforms sequential search under the same iteration budget, consistent with benefits from broader coverage of the search space. Further trajectory analysis shows that higher-performing models more effectively diagnose failures, revise search directions, and preserve the intended economic hypothesis when selecting candidates. These findings suggest that future progress in autonomous research will require stronger models together with adaptive policies for deploying test-time computation throughout the research process. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35559 — 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 2026-10-07T20:29:01.886Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).