Current Practices for Building LLM-Powered Reasoning Tools Are Ad Hoc -- and We Can Do Better

• URL: http://arxiv.org/abs/2507.05886v1
• Date: Tue, 08 Jul 2025 11:19:09 GMT
• Title: Current Practices for Building LLM-Powered Reasoning Tools Are Ad Hoc -- and We Can Do Better
• Authors: Aaron Bembenek,
• Abstract summary: I propose Neurosymbolic Transition Systems as a principled computational model that can underlie infrastructure for building neurosymbolic AR tools.<n>In this model, symbolic state is paired with intuition, and state transitions operate over symbols and intuition in parallel.<n>I argue why this new paradigm can scale logical reasoning beyond current capabilities while retaining the strong guarantees of symbolic algorithms.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There is growing excitement about building software verifiers, synthesizers, and other Automated Reasoning (AR) tools by combining traditional symbolic algorithms and Large Language Models (LLMs). Unfortunately, the current practice for constructing such neurosymbolic AR systems is an ad hoc programming model that does not have the strong guarantees of traditional symbolic algorithms, nor a deep enough synchronization of neural networks and symbolic reasoning to unlock the full potential of LLM-powered reasoning. I propose Neurosymbolic Transition Systems as a principled computational model that can underlie infrastructure for building neurosymbolic AR tools. In this model, symbolic state is paired with intuition, and state transitions operate over symbols and intuition in parallel. I argue why this new paradigm can scale logical reasoning beyond current capabilities while retaining the strong guarantees of symbolic algorithms, and I sketch out how the computational model I propose can be reified in a logic programming language.

Related papers

• A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning [0.0]
  General logical reasoning, defined as the ability to reason deductively on domain-agnostic tasks, continues to be a challenge for large language models (LLMs)<n>There has been a recent surge in interest in neurosymbolic AI, which attempts to incorporate logic into neural networks.<n>We first identify two main neurosymbolic approaches to improving logical reasoning.
  arXiv  Detail & Related papers  (2025-08-05T12:14:32Z)
• Standard Neural Computation Alone Is Insufficient for Logical Intelligence [3.230778132936486]
  We argue that standard neural layers must be fundamentally rethought to integrate logical reasoning.<n>We advocate for Logical Neural Units (LNUs)-modular components that embed differentiable approximations of logical operations.
  arXiv  Detail & Related papers  (2025-02-04T09:07:45Z)
• On Scaling Neurosymbolic Programming through Guided Logical Inference [1.124958340749622]
  We propose a new approach centered around an exact algorithmNL, that enables bypassing the computation of the logical provenance.<n>We show that this approach can be adapted for approximate reasoning with $epsilon$ or $(epsilon, delta)$ guarantees, called ApproxDPNL.
  arXiv  Detail & Related papers  (2025-01-30T08:49:25Z)
• Compositional Generalization Across Distributional Shifts with Sparse Tree Operations [77.5742801509364]
  We introduce a unified neurosymbolic architecture called the Differentiable Tree Machine.<n>We significantly increase the model's efficiency through the use of sparse vector representations of symbolic structures.<n>We enable its application beyond the restricted set of tree2tree problems to the more general class of seq2seq problems.
  arXiv  Detail & Related papers  (2024-12-18T17:20:19Z)
• Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents [55.63497537202751]
  Article explores the convergence of connectionist and symbolic artificial intelligence (AI) Traditionally, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic. Recent advancements in large language models (LLMs) highlight the potential of connectionist architectures in handling human language as a form of symbols.
  arXiv  Detail & Related papers  (2024-07-11T14:00:53Z)
• The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning [54.56905063752427]
  Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI systems. Existing pipelines that train the neural and symbolic components sequentially require extensive labelling. New architecture, NeSyGPT, fine-tunes a vision-language foundation model to extract symbolic features from raw data.
  arXiv  Detail & Related papers  (2024-02-02T20:33:14Z)
• Extensions to Generalized Annotated Logic and an Equivalent Neural Architecture [4.855957436171202]
  We propose a list of desirable criteria for neuro symbolic systems and examine how some of the existing approaches address these criteria. We then propose an extension to annotated generalized logic that allows for the creation of an equivalent neural architecture. Unlike previous approaches that rely on continuous optimization for the training process, our framework is designed as a binarized neural network that uses discrete optimization.
  arXiv  Detail & Related papers  (2023-02-23T17:39:46Z)
• Neuro-Symbolic Causal Reasoning Meets Signaling Game for Emergent Semantic Communications [71.63189900803623]
  A novel emergent SC system framework is proposed and is composed of a signaling game for emergent language design and a neuro-symbolic (NeSy) artificial intelligence (AI) approach for causal reasoning. The ESC system is designed to enhance the novel metrics of semantic information, reliability, distortion and similarity.
  arXiv  Detail & Related papers  (2022-10-21T15:33:37Z)
• Join-Chain Network: A Logical Reasoning View of the Multi-head Attention in Transformer [59.73454783958702]
  We propose a symbolic reasoning architecture that chains many join operators together to model output logical expressions. In particular, we demonstrate that such an ensemble of join-chains can express a broad subset of ''tree-structured'' first-order logical expressions, named FOET. We find that the widely used multi-head self-attention module in transformer can be understood as a special neural operator that implements the union bound of the join operator in probabilistic predicate space.
  arXiv  Detail & Related papers  (2022-10-06T07:39:58Z)
• VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming [3.759936323189418]
  We present VAEL, a neuro-symbolic generative model integrating variational autoencoders (VAE) with the reasoning capabilities of probabilistic logic (L) programming.
  arXiv  Detail & Related papers  (2022-02-07T10:16:53Z)
• Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks [65.23508422635862]
  We propose learning rules with the recently proposed logical neural networks (LNN) Compared to others, LNNs offer strong connection to classical Boolean logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable.
  arXiv  Detail & Related papers  (2021-12-06T19:38:30Z)
• SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming [15.814914345000574]
  We introduce SLASH -- a novel deep probabilistic programming language (DPPL) At its core, SLASH consists of Neural-Probabilistic Predicates (NPPs) and logical programs which are united via answer set programming. We evaluate SLASH on the benchmark data of MNIST addition as well as novel tasks for DPPLs such as missing data prediction and set prediction with state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-10-07T12:35:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.