% Generated by IEEEtran.bst, version: 1.12 (2007/01/11) \begin{thebibliography}{10} \providecommand{\url}[1]{#1} \csname url@samestyle\endcsname \providecommand{\newblock}{\relax} \providecommand{\bibinfo}[2]{#2} \providecommand{\BIBentrySTDinterwordspacing}{\spaceskip=0pt\relax} \providecommand{\BIBentryALTinterwordstretchfactor}{4} \providecommand{\BIBentryALTinterwordspacing}{\spaceskip=\fontdimen2\font plus \BIBentryALTinterwordstretchfactor\fontdimen3\font minus \fontdimen4\font\relax} \providecommand{\BIBforeignlanguage}[2]{{% \expandafter\ifx\csname l@#1\endcsname\relax \typeout{** WARNING: IEEEtran.bst: No hyphenation pattern has been}% \typeout{** loaded for the language `#1'. Using the pattern for}% \typeout{** the default language instead.}% \else \language=\csname l@#1\endcsname \fi #2}} \providecommand{\BIBdecl}{\relax} \BIBdecl \bibitem{hendrycks2021measuringmathematicalproblemsolving} \BIBentryALTinterwordspacing D.~Hendrycks, C.~Burns, S.~Kadavath, A.~Arora, S.~Basart, E.~Tang, D.~Song, and J.~Steinhardt, ``Measuring mathematical problem solving with the math dataset,'' 2021. [Online]. Available: \url{https://arxiv.org/abs/2103.03874} \BIBentrySTDinterwordspacing \bibitem{ahn2024largelanguagemodelsmathematical} \BIBentryALTinterwordspacing J.~Ahn, R.~Verma, R.~Lou, D.~Liu, R.~Zhang, and W.~Yin, ``Large language models for mathematical reasoning: Progresses and challenges,'' 2024. [Online]. Available: \url{https://arxiv.org/abs/2402.00157} \BIBentrySTDinterwordspacing \bibitem{cobbe2021trainingverifierssolvemath} \BIBentryALTinterwordspacing K.~Cobbe, V.~Kosaraju, M.~Bavarian, M.~Chen, H.~Jun, L.~Kaiser, M.~Plappert, J.~Tworek, J.~Hilton, R.~Nakano, C.~Hesse, and J.~Schulman, ``Training verifiers to solve math word problems,'' 2021. [Online]. Available: \url{https://arxiv.org/abs/2110.14168} \BIBentrySTDinterwordspacing \bibitem{hoffmann2022trainingcomputeoptimallargelanguage} \BIBentryALTinterwordspacing J.~Hoffmann, S.~Borgeaud, A.~Mensch, E.~Buchatskaya, T.~Cai, E.~Rutherford, D.~de~Las~Casas, L.~A. Hendricks, J.~Welbl, A.~Clark, T.~Hennigan, E.~Noland, K.~Millican, G.~van~den Driessche, B.~Damoc, A.~Guy, S.~Osindero, K.~Simonyan, E.~Elsen, J.~W. Rae, O.~Vinyals, and L.~Sifre, ``Training compute-optimal large language models,'' 2022. [Online]. Available: \url{https://arxiv.org/abs/2203.15556} \BIBentrySTDinterwordspacing \bibitem{hendrycksmath2021} D.~Hendrycks, C.~Burns, S.~Kadavath, A.~Arora, S.~Basart, E.~Tang, D.~Song, and J.~Steinhardt, ``Measuring mathematical problem solving with the math dataset,'' \emph{NeurIPS}, 2021. \bibitem{besiroglu2024chinchillascalingreplicationattempt} \BIBentryALTinterwordspacing T.~Besiroglu, E.~Erdil, M.~Barnett, and J.~You, ``Chinchilla scaling: A replication attempt,'' 2024. [Online]. Available: \url{https://arxiv.org/abs/2404.10102} \BIBentrySTDinterwordspacing \bibitem{besold2017neuralsymboliclearningreasoningsurvey} \BIBentryALTinterwordspacing T.~R. Besold, A.~d'Avila Garcez, S.~Bader, H.~Bowman, P.~Domingos, P.~Hitzler, K.-U. Kuehnberger, L.~C. Lamb, D.~Lowd, P.~M.~V. Lima, L.~de~Penning, G.~Pinkas, H.~Poon, and G.~Zaverucha, ``Neural-symbolic learning and reasoning: A survey and interpretation,'' 2017. [Online]. Available: \url{https://arxiv.org/abs/1711.03902} \BIBentrySTDinterwordspacing \bibitem{gao2023palprogramaidedlanguagemodels} \BIBentryALTinterwordspacing L.~Gao, A.~Madaan, S.~Zhou, U.~Alon, P.~Liu, Y.~Yang, J.~Callan, and G.~Neubig, ``Pal: Program-aided language models,'' 2023. [Online]. Available: \url{https://arxiv.org/abs/2211.10435} \BIBentrySTDinterwordspacing \bibitem{xu2024chatglmmathimprovingmathproblemsolving} \BIBentryALTinterwordspacing Y.~Xu, X.~Liu, X.~Liu, Z.~Hou, Y.~Li, X.~Zhang, Z.~Wang, A.~Zeng, Z.~Du, W.~Zhao, J.~Tang, and Y.~Dong, ``Chatglm-math: Improving math problem-solving in large language models with a self-critique pipeline,'' 2024. [Online]. Available: \url{https://arxiv.org/abs/2404.02893} \BIBentrySTDinterwordspacing \bibitem{petruzzellis2024assessingemergentsymbolicreasoning} \BIBentryALTinterwordspacing F.~Petruzzellis, A.~Testolin, and A.~Sperduti, ``Assessing the emergent symbolic reasoning abilities of llama large language models,'' 2024. [Online]. Available: \url{https://arxiv.org/abs/2406.06588} \BIBentrySTDinterwordspacing \end{thebibliography}