Metraipolis › archive › dc_464f3e20a3bc
TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts — arXiv:2610.06824
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06824
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:25:44.127Z
- SHA-256 of the archived text
8da21ff0f85f5dc3af13ccddfa8506aa33f4e1b3a84879db7c29c7cd4b6ec278- Stable URL of this page
https://metraipolis.com/documento/dc_464f3e20a3bc
How to cite
TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts — arXiv:2610.06824 — arXiv, https://arxiv.org/abs/2610.06824 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_464f3e20a3bc (Metraipolis archive dc_464f3e20a3bc, sha256 8da21ff0f85f5dc3af13ccddfa8506aa33f4e1b3a84879db7c29c7cd4b6ec278)
BibTeX
@misc{dc464f3e20a3bc,
title = {TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts — arXiv:2610.06824},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06824},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_464f3e20a3bc; sha256 8da21ff0f85f5dc3af13ccddfa8506aa33f4e1b3a84879db7c29c7cd4b6ec278},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06824. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experimental results. TasteVal measures the experimental component of research taste; given a fixed research problem, we measure how well a model iteratively designs experiments and draws conclusions from their outcomes. We operationalize experimental research taste as compute efficiency; a Researcher who reaches the same score as an expert human using half the serial experimental compute has twice the experimental taste. Experimental taste thus acts as a multiplier on experimental compute, making it a key input to forecasts of AI progress. TasteVal consists of 8 novel, challenging, open-ended tasks representative of frontier AI R&D. To isolate taste from coding ability, the model under evaluation acts as a Researcher that iteratively designs experiments while a fixed Coder agent implements them and reports their results. The Researcher executes until either the 40 H100 hour or 120 wall-clock hour budgets are exhausted. We recruit 24 human experts, at least 2 per task, and take the best expert attempt per task as the expert baseline. We evaluate 20 models released between 2023 and 2026. The best-performing model, Opus 5.5, exceeds our expert baseline, with a compute multiplier of 2.3x (95% CI 1.15-4.37), at roughly 1/30 of our baseliners' average per-run cost. On TasteVal, the compute multiplier of frontier models has doubled approximately every 3.0 months since December 2025 (95% CI 1.7-5.0), up from every 14 months between 2023 and December 2025. Measured by final normalized performance, frontier models show no trend break, doubling every 14.6 months. To keep TasteVal uncontaminated, we do not release the tasks. 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/2610.06824 — 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 2026-10-06T05:24:05.713Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).