@inproceedings{xu-etal-2026-adaptive,
    title = "Adaptive {LLM}-Symbolic Reasoning via Dynamic Logical Solver Composition",
    author = "Xu, Lei  and
      Beckmann, Pierre  and
      Valentino, Marco  and
      Freitas, Andre",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.eacl-long.54/",
    pages = "1187--1208",
    ISBN = "979-8-89176-380-7",
    abstract = "Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature, i.e., the integration of a target solver is predetermined at design time, hindering the ability to employ diverse formal inference strategies. To address this, we introduce an adaptive, multi-paradigm, neuro-symbolic inference framework that: (1) automatically identifies formal reasoning strategies from problems expressed in natural language; and (2) dynamically selects and applies specialized formal logical solvers via autoformalization interfaces. Extensive experiments on individual and multi-paradigm reasoning tasks support the following conclusions: LLMs are effective at predicting the necessary formal reasoning strategies with an accuracy above 90{\%}. This enables flexible integration with formal logical solvers, resulting in our framework outperforming competing baselines {--} by 17{\%} and 6{\%} compared to GPT-4o and DeepSeek-V3.1, respectively. Moreover, adaptive reasoning can even positively impact pure LLM methods, yielding gains of 10{\%}, 5{\%}, and 6{\%} on zero-shot, CoT, and CoT$_{sym}$ settings with GPT-4o. Finally, although smaller models struggle with adaptive neuro-symbolic reasoning, post-training offers a viable path to improvement. Overall, this work establishes the foundations for adaptive LLM-symbolic reasoning, offering a path forward for unifying material and formal inferences on heterogeneous reasoning challenges.The code and data are available at \url{https://github.com/idiap/adaptive_symbolic_reasoning}."
}