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

• URL: http://arxiv.org/abs/2604.02350v1
• Date: Thu, 19 Feb 2026 03:38:03 GMT
• Title: Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility
• Abstract summary: Differentiable Symbolic Planning (DSP) is a neural architecture that performs discrete symbolic reasoning.<n>We integrate DSP into a Universal Cognitive Kernel (UCK) that combines graph attention with iterative constraint propagation.<n>UCK+DSP achieves 97.4% accuracy on planning under 4x size generalization.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 negative classes where standard neural approaches collapse. Ablation studies reveal that global phi aggregation is critical: removing it causes accuracy to drop from 98% to 64%. The learned phi signal exhibits interpretable semantics, with values of +18 for feasible cases and -13 for infeasible cases emerging without supervision.

Related papers

• A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration [9.354331831290233]
  We propose Structural Dynamics Graph World Model as an executable backbone contract.<n>An optional bounded residual R concentrates learnability, while a global projection maps states to feasibility.<n>On a semi-synthetic floodbed and USGS streamflow, SD-GWM reduces constraint violations to floating-point tolerance.
  arXiv  Detail & Related papers  (2026-08-09T13:11:40Z)
• Neural Feature Governance: Extending Atom Prevalence [0.0]
  This paper introduces Neural Atom Prevalence (NAP), a principled Bayesian framework for structured node-level model selection in feedforward neural networks.<n>Nap achieves state-of-the-art structural sparsity, reducing active nodes to as few as 8% of the original dense architecture on MNIST.
  arXiv  Detail & Related papers  (2026-07-23T08:50:12Z)
• Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata [57.27430779838529]
  We present an exact and tractable algorithm for sampling from the constrained mean-field posterior under any constraint expressible as a finite automaton.<n>The approach guarantees constraint satisfaction by construction, supports both greedy and sampling-based decoding, and is compatible with parallel and block-wise decoding.<n> Empirical evaluations on Dream-7B and LLaDA-8 show substantial accuracy gains across various tasks.
  arXiv  Detail & Related papers  (2026-07-08T05:48:57Z)
• Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search [50.16356451328644]
  Proving Shannon-type entropy inequalities is a fundamental task in information theory.<n>We investigate whether small-scale large language models, fine-tuned on atomic proof steps, can automate this process.<n>We show that GPT-5.5 solves 1.7% samples under zero-shot prompting while Psitip solves 33.3% samples.
  arXiv  Detail & Related papers  (2026-06-04T05:43:12Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary [13.891522069967507]
  Extended chain-of-thought reasoning can degrade performance on deterministic state-tracking tasks.<n>We show that tool-integrated reasoning consistently outperforms neural chain-of-thought.<n>Our results provide principled guidance for when pure neural reasoning should yield to hybrid approaches in agentic systems.
  arXiv  Detail & Related papers  (2026-05-29T21:35:23Z)
• The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning [9.898274894485107]
  Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint.<n>We study this through a diagnose-measure-bridge-treat framework.
  arXiv  Detail & Related papers  (2026-03-30T21:36:09Z)
• AS2 -- Attention-Based Soft Answer Sets: An End-to-End Differentiable Neuro-Soft-Symbolic Reasoning Architecture [13.507142458358333]
  We introduce AS2 (Attention-Based Soft Answer Sets), a differentiable neuro-symbolic architecture that replaces a discrete solver with a soft approximation.<n>On Visual Sudoku, AS2 achieves 99.89% cell accuracy and 100% constraint satisfaction (verified by Clingo) across 1,000 test boards.<n>These results demonstrate that a soft differentiable fixpoint operator, combined with constraint-aware attention and declarative constraint specification, can match or exceed pipeline and solver-based neuro-symbolic systems.
  arXiv  Detail & Related papers  (2026-03-19T02:51:18Z)
• JANUS: Structured Bidirectional Generation for Guaranteed Constraints and Analytical Uncertainty [0.0]
  JANUS (Joint Ancestral Network for Uncertainty and Synthesis) is a framework that unifies capabilities using a DAG of Bayesian Decision Trees.<n>Key innovation is Reverse-Topological Back-filling, an algorithm that propagates constraints backwards through the causal graph.<n>Janus achieves state-of-the-art fidelity (Detection Score 0.497), eliminates mode collapse on imbalanced data, and provides exact handling of complex inter-column constraints.
  arXiv  Detail & Related papers  (2026-03-04T05:36:11Z)
• Semantic-Constrained Federated Aggregation: Convergence Theory and Privacy-Utility Bounds for Knowledge-Enhanced Distributed Learning [0.0]
  We introduce Semantic-Constrained Federated Aggregation (SCFA), a theoretically-grounded framework incorporating domain knowledge constraints into distributed optimization.<n>We prove SCFA convergence rate O(1/sqrt(T) + rho) where rho represents constraint violation rate, establishing the first convergence theory for constraint-based federated learning.<n>We validate our framework on manufacturing predictive maintenance using Bosch production data with 1.18 million samples and 968 sensor features.
  arXiv  Detail & Related papers  (2025-12-12T04:29:29Z)
• Beyond Mimicry: Preference Coherence in LLMs [0.19116784879310025]
  We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs.<n>We find 23 combinations (47.9%) demonstrated statistically significant relationships between scenario intensity and choice patterns.<n>Only 5 combinations (10.4%) demonstrate meaningful preference coherence through adaptive or threshold-based behavior.<n>The prevalence of unstable transitions (45.8%) and stimulus-specific sensitivities suggests current AI systems lack unified preference structures.
  arXiv  Detail & Related papers  (2025-11-17T17:41:48Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Semantic Strengthening of Neuro-Symbolic Learning [85.6195120593625]
  Neuro-symbolic approaches typically resort to fuzzy approximations of a probabilistic objective. We show how to compute this efficiently for tractable circuits. We test our approach on three tasks: predicting a minimum-cost path in Warcraft, predicting a minimum-cost perfect matching, and solving Sudoku puzzles.
  arXiv  Detail & Related papers  (2023-02-28T00:04:22Z)
• Semantic Probabilistic Layers for Neuro-Symbolic Learning [83.25785999205932]
  We design a predictive layer for structured-output prediction (SOP) It can be plugged into any neural network guaranteeing its predictions are consistent with a set of predefined symbolic constraints. Our Semantic Probabilistic Layer (SPL) can model intricate correlations, and hard constraints, over a structured output space.
  arXiv  Detail & Related papers  (2022-06-01T12:02:38Z)
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness [68.97830259849086]
  Most datasets only capture a simpler subproblem and likely suffer from spurious features. We study adversarial robustness - a local generalization property - to reveal hard, model-specific instances and spurious features. Unlike in other applications, where perturbation models are designed around subjective notions of imperceptibility, our perturbation models are efficient and sound. Surprisingly, with such perturbations, a sufficiently expressive neural solver does not suffer from the limitations of the accuracy-robustness trade-off common in supervised learning.
  arXiv  Detail & Related papers  (2021-10-21T07:28:11Z)
• Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction [54.06292969184476]
  We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Our approach employs semantic loss which captures the precise meaning of a logical sentence. With a focus on low-data regimes, we show that semantic loss outperforms the baselines by a wide margin.
  arXiv  Detail & Related papers  (2021-03-20T00:16:29Z)

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.