Symbolic Reasoning in Language Models

Follow this topic Ask about this topic

Latest papers

30 papers5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning
Nov 6, 2026Rosario Napoli, Antonio Celesti, Massimo Villari +1Graph Retrieval-Augmented Generation LLM Reasoning with Graphs
University of Messina, Messina, Italy
Generate-then-Rank: Learning Symbolic Goal Interpretation for Embodied Agents
Nov 5, 2026Jisen Lei, Huizhi LiangEmbodied AI Symbolic Reasoning in Language Models
School of Computing, Newcastle University, Newcastle upon Tyne, United Kingdom
ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme
Nov 3, 2026Aboubaker Seddiq Benterki, Jüri Vain, Gert Kanter +1Inductive Logic Programming Neuro-Symbolic Reasoning
Tallinn University of Technology (TalTech), Ehitajate tee 5, 19086 Tallinn, Estonia
Sketchpad: certified exact arithmetic with a small vision-language model
Nov 3, 2026Mostafa 'Neo' MohsenvandNumerical Reasoning in Language Models LLM Reliability
MIT Media Lab
Evolving Explanations: Complexity-Adaptive Refinement of Faithful Explanations for Symbolic Regression
Nov 2, 2026Elisabeth Mayrhuber, Ting Hu, Stephan WinklerExplainable Artificial Intelligence Faithfulness of Language Model Explanations
Bioinformatics Research Group, University of Applied Sciences Upper Austria · Computer Vision Lab, TU Wien, Vienna, Austria · Machine Intelligence and Biocomputing Laboratory, Queen’s University, Kingston, Canada
A Tool in the Forward Pass: Frozen Tape Modules as Layers of a Small Language Model
Oct 31, 2026Michael Granitzer, Saber Zerhoudi, Mohammad Al-Maamari +2LLM Tool Use Efficient Language Model Inference
University of Passau, Passau, Germany · IT:U Interdisciplinary Transformation University Austria, Linz, Austria
Specification-Guided Generation for Large Language Models
Oct 30, 2026Alessandro Previti, Konstantinos Vandikas, Mario Alviano +5Language Model Decoding Constrained Decoding
Ericsson AB, Stockholm, Sweden · DEMACS, University of Calabria, Rende, Italy · RISE Research Institutes of Sweden, Stockholm, Sweden
Hybrid AI Patterns: Thirteen Ways to Couple Language Models with Rules, and How to Choose Among Them
Oct 29, 2026Siegfried Handschuh, Götz-Henrik Wiegand, Lorena RaichleHybrid Language Models Symbolic Reasoning in Language Models
Institute of Computer Science, University of St. Gallen (HSG)
LGMT: A Tool for Testing the Logical Reasoning Reliability of LLMs
Oct 23, 2026Zenghui Zhou, Xiaoke Fang, Zheng ZhengReasoning Consistency in Language Models Language Model Reasoning Evaluation
School of Automation Science and Electrical Engineering, Beihang University Xueyuan Road, Haidian District, Beijing, 100191, China
Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog
Oct 8, 2026Hadeel Al-Negheimish, Jasna Ilieva, Yoon KimDeductive Reasoning in Language Models Long-Horizon LLM Reasoning
King Saud University · Massachusetts Institute of Technology
In-Context Learning Amplifies a Latent Symbolic Circuit
Sep 28, 2026Melissa WesselLLM Interpretability In-Context Learning
Independent Researcher.
A Verifier-Guided Explainable Reasoning Framework with Gold-Anchored QLoRA, Task-Aware Mixture-of-Experts, and Group-Relative RLVR
Sep 4, 2026Thi Kim Trang Vo, Nam Tien Le, Thi Kim Nguyet Vo +2Educational QA Symbolic Reasoning in Language Models
University of Information Technology (UIT), Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · Ho Chi Minh City University of Technology (HCMUT), Vietnam +2
A Pre-Specified Construction-Confirmation Test of Operation-Level Causal Transfer Across Finite Isomorphic Symbolic Domains
Aug 16, 2026Xinyi ShanSymbolic Reasoning in Language Models Causal Reasoning in Language Models
Independent Researcher
Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming
Jul 25, 2026Zirong Chen, Meiyi MaReasoning Trace Analysis Reasoning Consistency in Language Models
Department of Computer Science, Vanderbilt University, USA
Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities
Jul 22, 2026Hanna Abi Akl, Fabien Gandon, Catherine Faron +1Knowledge Representation Structured Reasoning
Université Côte d’Azur, Inria, CNRS, I3S, Sophia Antipolis, France · Data ScienceTech Institute, Paris, France
When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
Jun 28, 2026Zhengqi Pei, Qingming Huang, Shuhui WangMulti-Agent LLM Systems Efficient Language Model Reasoning
State Key Lab of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China
HOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs
Jun 22, 2026Yucheng Wu, Jundong Xu, Mingzhen Ju +4Logical Reasoning LLM Evaluation
State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University · School of Computing, National University of Singapore +3
SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance
Jun 8, 2026Hanna Abi Akl, Fabien Gandon, Catherine Faron +1Language Model Bias Evaluation Logical Reasoning
Université Côte d’Azur, Inria, CNRS, I3S, Sophia Antipolis, France · Data ScienceTech Institute, Paris, France
Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair
Jun 3, 2026Zehua Cheng, Wei Dai, Jiahao Sun +1LLM Reasoning Efficient Language Model Inference
Department of Computer Science, University of Oxford, UK · Institute of Logic and Computation, TU Wien, Austria
From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks
Apr 1, 2026Ayan Datta, Mounika Marreddy, Alexander Mehler +2Symbolic Reasoning in Language Models LLM Interpretability
IIIT Hyderabad · Goethe University, Frankfurt am Main, Germany · University of Sheffield, UK
Unveiling the Reasoning Process of Large Language Models
Mar 31, 2026Junjie Zhang, Zhen Shen, Xisong Dong +1Symbolic Reasoning in Language Models LLM Interpretability
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences
The Lattice Representation Hypothesis of Large Language Models
Mar 1, 2026Bo XiongSymbolic Reasoning in Language Models Representation Geometry in Language Models
Stanford University, United States
Neurosymbolic Language Reasoning as Satisfiability Modulo Theory
Feb 20, 2026Hyunseok Oh, Sam Stern, Youngki Lee +1Constraint-Guided Reasoning in Language Models Neuro-Symbolic Reasoning
Seoul National University · U. Mass. Amherst · Microsoft
Neuro-Symbolic Synergy for World Modeling
Feb 11, 2026Hongyu Zhao, Siyu Zhou, Haolin Yang +2LLM World Models World Model Learning
Department of Computer Science University of Maryland College Park, MD 20742, USA · Faculty of Engineering and IT Australian AI Institute University of Technology Sydney Sydney, Australia · Department of Statistics University of Chicago Chicago, IL 60637, USA +2
ChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems
Jan 5, 2026Noel ThomasSymbolic Reasoning in Language Models LLM Reasoning
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Semantic Deception: When Reasoning Models Can't Compute an Addition
Dec 23, 2025Nathaniël de Leeuw, Marceau Nahon, Mathis Reymond +2Language Model Reasoning Evaluation Symbolic Reasoning in Language Models
Institute of Intelligent Systems and Robotics, CNRS, Sorbonne University, Paris, F-75005, France. · Paris Cit´e University, Paris, F-75006, France.
Training Language Models to Use Prolog as a Tool
Dec 8, 2025Niklas Mellgren, Peter Schneider-Kamp, Lukas Galke PoechReward Hacking Logical Reasoning
University of Southern Denmark
EngTrace: A Symbolic Benchmark for Verifiable Process Evaluation of Engineering Reasoning
Nov 3, 2025Ayesha Gull, Muhammad Usman Safder, Rania Elbadry +4Language Model Reasoning Evaluation Symbolic Reasoning in Language Models
Namal University · MBZUAI · The University of Tokyo
Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers
Sep 27, 2025Tian Qin, Yuhan Chen, Zhiwei Wang +1Transformer Symbolic Reasoning in Language Models
School of Mathematical Sciences, Shanghai Jiao Tong University · School of Mathematics and Statistics, Wuhan University · Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University
Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Bootstrapped Prolog-based Chain-of-Thought
Jul 18, 2024Xihe Qiu, Yongxin Deng, Xiaoyu Tan +2Symbolic Reasoning in Language Models LLM Training
Shanghai University of Engineering Science · National University of Singapore · University of Technology Sydney

Nov 6, 2026J/K move · Enter open · S save

Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning

Rosario Napoli, Antonio Celesti, Massimo Villari, Maria Fazio

University of Messina, Messina, Italy

Graph Retrieval-Augmented Generation LLM Reasoning with Graphs Agentic RAG Symbolic Reasoning in Language Models

Open paper AskPDF arXiv

Knowledge Graphs (KGs) and Large Language Models (LLMs) represent two approaches for knowledge representation and reasoning over heterogeneous data. Recent research has explored their integration through Graph Retrieval-Augmented Generation (GraphRAG) systems, which use KGs to provide structured context to LLMs. However, existing GraphRAG approaches treat KGs as homogeneous graphs and rely on textual similarity between the input prompt and the context, rather than using it as a source of deterministic knowledge. This work proposes an agent-based GraphRAG system that introduces a symbolic layer to integrate deterministic reasoning alongside text similarities. This approach is based on the definition of typed centralities for KGs, where centrality measures are computed separately for each specific KG's class. This information is used to construct a symbolic representation that is provided to the LLM as a deterministic source. The proposed system was mathematically validated and evaluated on a real-world POLE (Person, Object, Location, Event) dataset, comparing reasoning and information retrieval with and without the symbolic layer. The results indicate that the our approach leads to responses that are more consistent with the context, improving the generated outputs.