Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition

Lei Xu, Pierre Beckmann, Marco Valentino, Andre Freitas


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 CoTsym 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 https://github.com/idiap/adaptive_symbolic_reasoning.
Anthology ID:
2026.eacl-long.54
Volume:
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Vera Demberg, Kentaro Inui, Lluís Marquez
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1187–1208
Language:
URL:
https://aclanthology.org/2026.eacl-long.54/
DOI:
Bibkey:
Cite (ACL):
Lei Xu, Pierre Beckmann, Marco Valentino, and Andre Freitas. 2026. Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1187–1208, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition (Xu et al., EACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eacl-long.54.pdf
Checklist:
 2026.eacl-long.54.checklist.pdf