REASON: Accelerating Probabilistic Logical Reasoning for Scalable Neuro-Symbolic Intelligence

• URL: http://arxiv.org/abs/2601.20784v1
• Date: Wed, 28 Jan 2026 17:17:21 GMT
• Title: REASON: Accelerating Probabilistic Logical Reasoning for Scalable Neuro-Symbolic Intelligence
• Authors: Zishen Wan, Che-Kai Liu, Jiayi Qian, Hanchen Yang, Arijit Raychowdhury, Tushar Krishna,
• Abstract summary: This paper presents REASON, an integrated acceleration framework for probabilistic logical reasoning in neuro-symbolic AI.<n>REASON introduces a unified directed acyclic graph representation that captures common structure across symbolic and probabilistic models.<n>REASON is tightly integrated with GPU streaming multiprocessors through a programmable interface and multi-level pipeline.
• Score: 7.533896918107583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neuro-symbolic AI systems integrate neural perception with symbolic reasoning to enable data-efficient, interpretable, and robust intelligence beyond purely neural models. Although this compositional paradigm has shown superior performance in domains such as reasoning, planning, and verification, its deployment remains challenging due to severe inefficiencies in symbolic and probabilistic inference. Through systematic analysis of representative neuro-symbolic workloads, we identify probabilistic logical reasoning as the inefficiency bottleneck, characterized by irregular control flow, low arithmetic intensity, uncoalesced memory accesses, and poor hardware utilization on CPUs and GPUs. This paper presents REASON, an integrated acceleration framework for probabilistic logical reasoning in neuro-symbolic AI. REASON introduces a unified directed acyclic graph representation that captures common structure across symbolic and probabilistic models, coupled with adaptive pruning and regularization. At the architecture level, REASON features a reconfigurable, tree-based processing fabric optimized for irregular traversal, symbolic deduction, and probabilistic aggregation. At the system level, REASON is tightly integrated with GPU streaming multiprocessors through a programmable interface and multi-level pipeline that efficiently orchestrates compositional execution. Evaluated across six neuro-symbolic workloads, REASON achieves 12-50x speedup and 310-681x energy efficiency over desktop and edge GPUs under TSMC 28 nm node. REASON enables real-time probabilistic logical reasoning, completing end-to-end tasks in 0.8 s with 6 mm2 area and 2.12 W power, demonstrating that targeted acceleration of probabilistic logical reasoning is critical for practical and scalable neuro-symbolic AI and positioning REASON as a foundational system architecture for next-generation cognitive intelligence.

Related papers

• Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis [50.20709408241935]
  This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture.<n>Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs)<n>GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters.
  arXiv  Detail & Related papers  (2026-02-13T04:38:51Z)
• DeepProofLog: Efficient Proving in Deep Stochastic Logic Programs [30.18197334181211]
  This paper introduces DeepProofLog, a novel NeSy system based on logic programs.<n>DPrL parameterizes all derivation steps with neural networks, allowing efficient neural guidance over the proving system.<n>Our experiments on standard NeSy benchmarks and knowledge graph reasoning tasks demonstrate that DPrL outperforms existing state-of-the-art NeSy systems.
  arXiv  Detail & Related papers  (2025-11-11T18:58:03Z)
• FuncGNN: Learning Functional Semantics of Logic Circuits with Graph Neural Networks [0.0]
  And-Inverter Graph synthesiss (AIGs) are widely adopted for representing Boolean logic in modern circuits.<n>We propose FuncGNN, which integrates hybrid feature aggregation to extract multi-granularity topological patterns.<n>FuncGNN achieves improvements of 2.06% and 18.71%, respectively, while reducing training time by approximately 50.6% and GPU memory usage by about 32.8%.
  arXiv  Detail & Related papers  (2025-06-07T13:04:07Z)
• 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)
• Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture [22.274696991107206]
  Neuro-symbolic AI emerges as a promising paradigm, fusing neural and symbolic approaches to enhance interpretability, robustness, and trustworthiness. Recent neuro-symbolic systems have demonstrated great potential in collaborative human-AI scenarios with reasoning and cognitive capabilities. We first systematically categorize neuro-symbolic AI algorithms, and then experimentally evaluate and analyze them in terms of runtime, memory, computational operators, sparsity, and system characteristics.
  arXiv  Detail & Related papers  (2024-09-20T01:32:14Z)
• Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning [91.29876772547348]
  Spiking neural networks (SNNs) are investigated as biologically inspired models of neural computation. This paper reveals that SNNs, when amalgamated with synaptic delay and temporal coding, are proficient in executing (knowledge) graph reasoning.
  arXiv  Detail & Related papers  (2024-05-27T05:53:30Z)
• 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)
• LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning [73.98142349171552]
  LOGICSEG is a holistic visual semantic that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. During fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models.
  arXiv  Detail & Related papers  (2023-09-24T05:43:19Z)
• 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)
• Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions [50.674773358075015]
  We propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers. We show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
  arXiv  Detail & Related papers  (2021-07-07T16:59:14Z)

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.