Metraipolis › archive › dc_2f172e389fc4
Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference — arXiv:2609.05842
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05842
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:58:45.469Z
- SHA-256 of the archived text
8be536552e9755d5d5bef2d27d52255b629bdc85449eec615882be48fe630e07- Stable URL of this page
https://metraipolis.com/documento/dc_2f172e389fc4
How to cite
Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference — arXiv:2609.05842 — arXiv (en), https://arxiv.org/abs/2609.05842 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f172e389fc4 (Metraipolis archive dc_2f172e389fc4, sha256 8be536552e9755d5d5bef2d27d52255b629bdc85449eec615882be48fe630e07)
BibTeX
@misc{dc2f172e389fc4,
title = {Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference — arXiv:2609.05842},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05842},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f172e389fc4; sha256 8be536552e9755d5d5bef2d27d52255b629bdc85449eec615882be48fe630e07},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05842. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement learning with verifiable rewards enables large language models to think slowly, but the same training can induce policy collapse: probability concentrates onto a few successful trajectories and exploratory diversity erodes. We ask whether quantum AI can realize slow thinking differently. We formulate slow thinking as coherent dynamics over reasoning trajectories, a discrete path integral in which action sequences coexist in superposition and recombine before measurement. In our trainable realization, an exact verifier partitions the ensemble into collective accepted and rejected components that interfere under Grover amplitude amplification. A finite Grover evolution is maximized when the pre-amplification success probability lies at an analytically determined value below one, so inference itself defines an interior training target and removes the monotonic pressure toward unit success. In exact statevector simulations of a 2x3 sliding puzzle, Grover training reaches accuracy 0.95 on a 32-question training set at one round, against 0.73 for the strongest classical control. On held-out questions specialization has a cost: an untrained uniform policy read out through the same amplification remains the strongest reference on this solution-dense benchmark, and quantum training preserves far more held-out accuracy than classical training - at four rounds with matched circuit applications the two quantum models reach 3.2 and 3.9 times the strongest classical controls. The number of training questions supported by fixed-size policies trained at each amplification budget also grows faster with the budget than with matched classical repetition. These results establish a Grover-based realization of path-integral slow thinking: the interior target preserves exploratory path diversity, and ensemble-level interference converts it into verified performance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Quantum Physics (quant-ph) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.05842 — 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 2026-10-16T13:39:43.133Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).