- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Letter
  • Open Access

Adaptive strategy automation with large language models in paradoxical games

Kang Hao Cheong1,2,*, Jie Zhao1, and Tao Wen1

  • *Contact author: kanghao.cheong@ntu.edu.sg
PDF

Phys. Rev. Research 7, L022012 – Published 10 April, 2025

DOI: https://doi.org/10.1103/PhysRevResearch.7.L022012

Abstract

Finding an ideal sequence in games is crucial for maximizing gains in various scenarios. This process requires extensive investigation, which is both time consuming and demands significant domain expertise. The emergence of large language models (LLMs) represents a significant turning point in addressing this issue, attributable to their potent analytical capabilities. In this context, LLMs can serve to substantially alleviate the human labor needed to manage these complexities. Through comprehensive simulations of coin-tossing games, we have demonstrated that the adaptive switching strategies formulated by LLMs surpass predefined sequences in profitability when applied to certain paradoxical games. Furthermore, our experimental findings indicate that the proposed method not only automates the identification of effective strategies but also provides adaptability to various forms of these paradoxical games.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (34)

  1. G. P. Harmer and D. Abbott, Losing strategies can win by Parrondo's paradox, Nature (London) 402, 864 (1999).
  2. T. Wen, J. W. Lai, and K. H. Cheong, Switching between two losing stocks may enable paradoxical win: An empirical analysis, Fractals 31, 2340001 (2023).
  3. D. K. Panda, B. V. Govind, and C. Benjamin, Generating highly entangled states via discrete-time quantum walks with Parrondo sequences, Physica A 608, 128256 (2022).
  4. J. Rajendran and C. Benjamin, Implementing Parrondo's paradox with two-coin quantum walks, R. Soc. Open Sci. 5, 171599 (2018).
  5. Z. Walczak and J. H. Bauer, Noise-induced Parrondo's paradox in discrete-time quantum walks, Phys. Rev. E 108, 044212 (2023).
  6. Z. Walczak and J. H. Bauer, Parrondo's paradox in quantum walks with three coins, Phys. Rev. E 105, 064211 (2022).
  7. T. Wen and K. H. Cheong, Parrondo's paradox reveals counterintuitive wins in biology and decision making in society, Phys. Life Rev. 51, 33 (2024).
  8. K. H. Cheong, T. Wen, S. Benler, J. M. Koh, and E. V. Koonin, Alternating lysis and lysogeny is a winning strategy in bacteriophages due to Parrondo's paradox, Proc. Natl. Acad. Sci. USA 119, e2115145119 (2022).
  9. J. M. Koh and K. H. Cheong, New doubly-anomalous Parrondo's games suggest emergent sustainability and inequality, Nonlinear Dyn. 96, 257 (2019).
  10. Y. Ye, Z.-Y. Zhai, X.-R. Hang, and N.-G. Xie, Influence analysis of network evolution on Parrondo effect, Biosystems 236, 105124 (2024).
  11. N.-G. Xie, J.-Y. Guo, Y. Ye, C. Wang, and L. Wang, The paradox of group behaviors based on Parrondo's games, Physica A 391, 6146 (2012).
  12. K. H. Cheong, D. B. Saakian, and R. Zadourian, Allison mixture and the two-envelope problem, Phys. Rev. E 96, 062303 (2017).
  13. J. W. Lai and K. H. Cheong, Chaotic switching for quantum coin Parrondo's games with application to encryption, Phys. Rev. Res. 3, L022019 (2021).
  14. T. Wen, K. H. Cheong, J. W. Lai, J. M. Koh, and E. V. Koonin, Extending the lifespan of multicellular organisms via periodic and stochastic intercellular competition, Phys. Rev. Lett. 128, 218101 (2022).
  15. K. H. Cheong, T. Wen, and J. W. Lai, Relieving cost of epidemic by Parrondo's paradox: A COVID-19 case study, Adv. Sci. 7, 2002324 (2020).
  16. L. Dinis and J. M. R. Parrondo, Optimal strategies in collective Parrondo games, Europhys. Lett. 63, 319 (2003).
  17. L. Dinis, Optimal sequence for Parrondo games, Phys. Rev. E 77, 021124 (2008).
  18. J. Zhao, Z. Wang, J. Cao, and K. H. Cheong, A self-adaptive evolutionary deception framework for community structure, IEEE Trans. Syst. Man Cybern., Syst. 53, 4954 (2023).
  19. J. Zhao and K. H. Cheong, Obfuscating community structure in complex network with evolutionary divide-and-conquer strategy, IEEE Trans. Evol. Comput. 27, 1926 (2023).
  20. D. Wu and K. Y. Szeto, Applications of genetic algorithm on optimal sequence for Parrondo games, in Proceedings of the International Conference on Evolutionary Computation Theory and Applications (ACM, New York, 2014), p. 30.
  21. D. Wu and K. Y. Szeto, Sequence analysis with motif-preserving genetic algorithm for iterated Parrondo games, in Computational Intelligence: International Joint Conference, IJCCI 2014, edited by J. J. Merelo et al., Studies in Computational Intelligence Vol. 620 (Springer, Berlin, 2016), pp. 33–48.
  22. T. Wen, E. V. Koonin, and K. H. Cheong, How flexible parasites can outsmart their hosts for evolutionary dominance, Phys. Rev. Res. 6, 023104 (2024).
  23. X. Molinero and C. Mégnien, Markov chains applied to Parrondo's paradox: the coin tossing problem. in 12th International Conference on Advanced Information Technologies and Applications (ICAITA, 2023).
  24. K. W. Cheung, H. F. Ma, D. Wu, G. C. Lui, and K. Y. Szeto, Winning in sequential Parrondo games by players with short-term memory, J. Stat. Mech. (2016) 054042.
  25. S. Rahmann, Optimal adaptive strategies for games of the Parrondo type, Science Direct Working Paper No. S1574-0358(04)70285-3 (2002), https://ssrn.com/abstract=3137703.
  26. K. H. Cheong and J. Zhao, Adaptive strategy optimization in game-theoretic paradigm using reinforcement learning, Phys. Rev. Res. 6, L032009 (2024).
  27. V. Capraro, R. Di Paolo, M. Perc, and V. Pizziol, Language-based game theory in the age of artificial intelligence, J. R. Soc. Interface 21, 20230720 (2024).
  28. Y. Chen, T. X. Liu, Y. Shan, and S. Zhong, The emergence of economic rationality of GPT, Proc. Natl. Acad. Sci. USA. 120, e2316205120 (2023).
  29. Q. Mei, Y. Xie, W. Yuan, and M. O. Jackson, A Turing test of whether AI chatbots are behaviorally similar to humans, Proc. Natl. Acad. Sci. USA 121, e2313925121 (2024).
  30. V. Capraro, R. Di Paolo, and V. Pizziol, Assessing large language models' ability to predict how humans balance self-interest and the interest of others, arXiv:2307.12776.
  31. V. Capraro, A. Lentsch, D. Acemoglu, S. Akgun, A. Akhmedova, E. Bilancini, J.-F. Bonnefon, P. Brañas-Garza, L. Butera, K. M. Douglas et al., The impact of generative artificial intelligence on socioeconomic inequalities and policy making, PNAS Nexus 3, 191 (2024).
  32. Raúl Toral, Cooperative Parrondo's games, Fluctuation Noise Lett. 01, L7 (2001).
  33. J.-Y. Yao, K.-P. Ning, Z.-H. Liu, M.-N. Ning, and L. Yuan, LLM lies: Hallucinations are not bugs, but features as adversarial examples, arXiv:2310.01469.
  34. H. Duan, Y. Yang, and K. Y. Tam, Do LLMs know about hallucination? An empirical investigation of LLM's hidden states, arXiv:2402.09733.

Outline

Information

Phys. Rev. Research 7, L022012– Published 10 April, 2025
  • Received 26 July 2024
  • Accepted 15 November 2024
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation