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

TL;DR

REASON tackles the bottleneck of probabilistic logical reasoning in neuro-symbolic AI by introducing a cross-layer co-design: a unified DAG representation with adaptive pruning and regularization at the algorithm level, a reconfigurable tree-based hardware fabric for symbolic and probabilistic computations, and tight GPU integration with a two-level execution pipeline at the system level. The framework is validated across six neuro-symbolic workloads, achieving substantial improvements in speed (12–50x) and energy efficiency (310–681x) over desktop and edge GPUs, and enabling real-time end-to-end reasoning on modest hardware. Key contributions include a DAG-based unification of FOL, SAT, PCs, and HMMs; semantics-preserving pruning and two-input regularization to reduce complexity; a tree-PE architecture with bespoke memory and scheduling support; and an end-to-end system integration that minimizes data movement while co-scheduling with neural pipelines. Collectively, REASON demonstrates that targeted algorithm-hardware co-design is essential for practical, scalable neuro-symbolic AI and positions the approach as a foundation for next-generation cognitive systems that blend structured reasoning with neural perception.

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.

Figures (13)

• Figure 1: Neuro-symbolic algorithmic flow and operations. The neural module serves as a perceptual and intuitive engine for representation learning, while the symbolic module performs structured logical reasoning with probabilistic inference. This compositional pipeline enables complex cognitive tasks across diverse scenarios.
• Figure 2: Scaling performance and efficiency.(a)-(c) Task accuracy of compositional LLM-symbolic models (C) and monolithic LLMs (M - shown in gray) across model sizes on complex reasoning, mathematical reasoning, and question-answering tasks. (d) Runtime efficiency comparison between LLM-symbolic models and RL-based CoT models on mathematical reasoning tasks wan2026compositional.
• Figure 3: End-to-end neuro-symbolic workload characterization.(a) Benchmark six neuro-symbolic workloads (AlphaGeometry, R$^2$-Guard, GeLaTo, Ctrl-G, NeuroPC, LINC) on CPU+GPU system, showing symbolic and probabilistic may serve as system bottlenecks. (b) Benchmark neuro-symbolic workloads on tasks with different scales, indicating that real-time performance cannot be satisfied and the potential efficiency issues. (c) Benchmark on A6000 and Orin GPU. (d) Roofline analysis, indicating server memory-bound of symbolic and probabilistic kernels.
• Figure 4: REASON overview.REASON is an integrated acceleration framework for probabilistic logical reasoning grounded neuro-symbolic AI with the goal to achieve efficient and scalable agentic cognition. REASON addresses the challenges of irregular compute and memory, symbolic and probabilistic latency bottleneck, and hardware underutilization, by proposing methodologies including unified DAG representation, reconfigurable PE, efficient dataflow, mapping, scalable architecture, two-level parallelism and programming interface. REASON is deployed across cognitive tasks and consistently demonstrates performance-efficiency improvements for compositional neuro-symbolic systems.
• Figure 5: Unified DAG representations of neuro-symbolic kernels. Logical (SAT/FOL), probabilistic (PC), and sequential (HMM) reasoning are expressed using DAG abstraction. Nodes represent atomic reasoning operations, edges encode dependency structure, and graph traversals implement inference procedures. This unification enables shared compilation, pruning, and hardware mapping in REASON.