Cover Image

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Noël, Valentin
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language Logic in Computer Science
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Geometry of Reasoning: Flowing Logics in Representation Space
by: Zhou, Yufa, et al.
Published: (2025)

REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning
by: Shen, Ziju, et al.
Published: (2025)

FLARE: Faithful Logic-Aided Reasoning and Exploration
by: Arakelyan, Erik, et al.
Published: (2024)

Reasoning Inconsistencies and How to Mitigate Them in Deep Learning
by: Arakelyan, Erik
Published: (2025)

Are Language Models Efficient Reasoners? A Perspective from Logic Programming
by: Opedal, Andreas, et al.
Published: (2025)

Formal Mathematical Reasoning: A New Frontier in AI
by: Yang, Kaiyu, et al.
Published: (2024)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
by: Su, DiJia, et al.
Published: (2025)

JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models
by: Chen, Michael K., et al.
Published: (2025)

SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas
by: Wei, Anjiang, et al.
Published: (2025)

Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation
by: Bao, Qiming, et al.
Published: (2022)

Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models
by: Qasim, Kaleem Ullah, et al.
Published: (2025)

Mathematics with large language models as provers and verifiers
by: Duc, Hieu Le, et al.
Published: (2025)

Bolzano: Case Studies in LLM-Assisted Mathematical Research
by: Balko, Martin, et al.
Published: (2026)

Lattice Annotated Temporal (LAT) Logic for Non-Markovian Reasoning
by: Mukherji, Kaustuv, et al.
Published: (2025)

Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
by: Bourigault, Pauline, et al.
Published: (2026)

PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
by: Tsoukalas, George, et al.
Published: (2024)

Chronosymbolic Learning: Efficient CHC Solving with Symbolic Reasoning and Inductive Learning
by: Luo, Ziyan, et al.
Published: (2023)

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
by: Cao, Chuxue, et al.
Published: (2025)

Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning
by: Ganguly, Debargha, et al.
Published: (2024)

Temporal Inductive Logic Reasoning over Hypergraphs
by: Yang, Yuan, et al.
Published: (2022)

Efficient Certified Reasoning for Binarized Neural Networks
by: Yang, Jiong, et al.
Published: (2025)

Inference of Abstraction for a Unified Account of Reasoning and Learning
by: Kido, Hiroyuki
Published: (2024)

Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey
by: DeLong, Lauren Nicole, et al.
Published: (2023)

Can Transformers Reason Logically? A Study in SAT Solving
by: Pan, Leyan, et al.
Published: (2024)

GLIDR: Graph-Like Inductive Logic Programming with Differentiable Reasoning
by: Johnson, Blair, et al.
Published: (2025)

MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs
by: Pati, Viresh, et al.
Published: (2026)

Structured Abductive-Deductive-Inductive Reasoning for LLMs via Algebraic Invariants
by: Gilda, Sankalp, et al.
Published: (2026)

Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations
by: Zhapa-Camacho, Fernando, et al.
Published: (2025)

A Logic for Reasoning About Aggregate-Combine Graph Neural Networks
by: Nunn, Pierre, et al.
Published: (2024)

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
by: Su, DiJia, et al.
Published: (2024)

Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
by: Morishita, Terufumi, et al.
Published: (2024)

SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
by: Zhao, Yanxiao, et al.
Published: (2025)

Advocate for Complete Benchmarks for Formal Reasoning with Formal/Informal Statements and Formal/Informal Proofs
by: Yousefzadeh, Roozbeh, et al.
Published: (2025)

Controlling Logical Collapse in LLMs via Algebraic Ontology Projection over F2
by: Miyashita, Hisashi, et al.
Published: (2026)

ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
by: Ahuja, Riyaz, et al.
Published: (2026)

Transformers Can Learn Connectivity in Some Graphs but Not Others
by: Roy, Amit, et al.
Published: (2025)

Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
by: Bao, Qiming, et al.
Published: (2025)

Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving
by: Rajaee, Sara, et al.
Published: (2025)

SubgoalXL: Subgoal-based Expert Learning for Theorem Proving
by: Zhao, Xueliang, et al.
Published: (2024)

RLSF: Fine-tuning LLMs via Symbolic Feedback
by: Jha, Piyush, et al.
Published: (2024)