[2604.02350] Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility

Computer Science > Machine Learning arXiv:2604.02350 (cs) [Submitted on 19 Feb 2026] Title:Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility Authors:Venkatakrishna Reddy Oruganti View a PDF of the paper titled Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility, by Venkatakrishna Reddy Oruganti View PDF HTML (experimental) Abstract:Neural networks excel at pattern recognition but struggle with constraint reasoning -- determining whether configurations satisfy logical or physical constraints. We introduce Differentiable Symbolic Planning (DSP), a neural architecture that performs discrete symbolic reasoning while remaining fully differentiable. DSP maintains a feasibility channel (phi) that tracks constraint satisfaction evidence at each node, aggregates this into a global feasibility signal (Phi) through learned rule-weighted combination, and uses sparsemax attention to achieve exact-zero discrete rule selection. We integrate DSP into a Universal Cognitive Kernel (UCK) that combines graph attention with iterative constraint propagation. Evaluated on three constraint reasoning benchmarks -- graph reachability, Boolean satisfiability, and planning feasibility -- UCK+DSP achieves 97.4% accuracy on planning under 4x size generalization (vs. 59.7% for ablated baselines), 96.4% on SAT under 2x generalization, and maintains balanced performance on both positive and negati...