Neuro-Symbolic Synergy for Interactive World Modeling

• URL: http://arxiv.org/abs/2602.10480v2
• Date: Thu, 12 Feb 2026 15:42:18 GMT
• Title: Neuro-Symbolic Synergy for Interactive World Modeling
• Authors: Hongyu Zhao, Siyu Zhou, Haolin Yang, Zengyi Qin, Tianyi Zhou,
• Abstract summary: We propose Neuro-Symbolic Synergy (NeSyS), a framework that integrates the probabilistic semantic priors of large language models with executable symbolic rules.<n>NeSyS alternates training between the two models using trajectories inadequately explained by the other.
• Score: 20.07686289460334
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs), where strict compliance with deterministic transition rules--particularly in corner cases--is essential. In contrast, Symbolic WMs provide logical consistency but lack semantic expressivity. To bridge this gap, we propose Neuro-Symbolic Synergy (NeSyS), a framework that integrates the probabilistic semantic priors of LLMs with executable symbolic rules to achieve both expressivity and robustness. NeSyS alternates training between the two models using trajectories inadequately explained by the other. Unlike rule-based prompting, the symbolic WM directly constrains the LLM by modifying its output probability distribution. The neural WM is fine-tuned only on trajectories not covered by symbolic rules, reducing training data by 50% without loss of accuracy. Extensive experiments on three distinct interactive environments, i.e., ScienceWorld, Webshop, and Plancraft, demonstrate NeSyS's consistent advantages over baselines in both WM prediction accuracy and data efficiency.

Related papers

• ICON: Invariant Counterfactual Optimization with Neuro-Symbolic Priors for Text-Based Person Search [6.247167721048087]
  Text-Based Person Search holds unique value in real-world surveillance bridging visual perception and language understanding.<n>Current paradigms utilizing pre-training models often fail to transfer effectively to complex open-world scenarios.<n>This paper proposes ICON, a framework integrating causal and topological priors.
  arXiv  Detail & Related papers  (2026-01-22T13:09:22Z)
• Stable Language Guidance for Vision-Language-Action Models [62.80963701282789]
  Residual Semantic Steering is a probabilistic framework that disentangles physical affordance from semantic execution.<n> RSS achieves state-of-the-art robustness, maintaining performance even under adversarial linguistic perturbations.
  arXiv  Detail & Related papers  (2026-01-07T16:16:10Z)
• CodeBrain: Towards Decoupled Interpretability and Multi-Scale Architecture for EEG Foundation Model [52.466542039411515]
  EEG foundation models (EFMs) have emerged to address the scalability issues of task-specific models.<n>We present CodeBrain, a two-stage EFM designed to fill this gap.<n>In the first stage, we introduce the TFDual-Tokenizer, which decouples heterogeneous temporal and frequency EEG signals into discrete tokens.<n>In the second stage, we propose the multi-scale EEGSSM architecture, which combines structured global convolution with sliding window attention.
  arXiv  Detail & Related papers  (2025-06-10T17:20:39Z)
• Incentivizing Multimodal Reasoning in Large Models for Direct Robot Manipulation [89.5123417007126]
  We show how to make Large Multimodal Models (LMMs) understand the spatial action space.<n>We also show how to fully exploit the reasoning capacity of LMMs in solving these tasks.<n>Our resulting reasoning model built upon a 7B backbone, named ReasonManip, demonstrates three notable advantages.
  arXiv  Detail & Related papers  (2025-05-19T06:00:14Z)
• Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision Transformers [1.3812010983144802]
  Recent neuro-symbolic approaches have successfully extracted symbolic rule-sets from CNN-based models to enhance interpretability.<n>We propose a framework for symbolic rule extraction from Vision Transformers (ViTs) by introducing a sparse concept layer inspired by Sparse Autoencoders (SAEs)<n>Our method achieves a 5.14% better classification accuracy than the standard ViT while enabling symbolic reasoning.
  arXiv  Detail & Related papers  (2025-05-10T19:45:15Z)
• PhysLLM: Harnessing Large Language Models for Cross-Modal Remote Physiological Sensing [49.243031514520794]
  Large Language Models (LLMs) excel at capturing long-range signals due to their text-centric design.<n>PhysLLM achieves state-the-art accuracy and robustness, demonstrating superior generalization across lighting variations and motion scenarios.
  arXiv  Detail & Related papers  (2025-05-06T15:18:38Z)
• DMWM: Dual-Mind World Model with Long-Term Imagination [43.39205414684229]
  We propose a novel dual-mind world model (DMWM) framework that integrates logical reasoning to enable imagination with logical consistency.<n>The proposed framework is evaluated on benchmark tasks that require long-term planning from the DMControl suite.
  arXiv  Detail & Related papers  (2025-02-11T14:40:57Z)
• Neurosymbolic AI for Travel Demand Prediction: Integrating Decision Tree Rules into Neural Networks [21.445133878049333]
  This study introduces a Neurosymbolic Artificial Intelligence (Neurosymbolic AI) framework that integrates decision tree (DT)-based symbolic rules with neural networks (NNs) to predict travel demand.
  arXiv  Detail & Related papers  (2025-02-02T05:10:31Z)
• Neuro-Symbolic Entity Alignment via Variational Inference [27.4635535516158]
  NeuSymEA is a unified neuro-symbolic reasoning framework.<n>It exploits the cross-KG structural pattern for robust entity alignment.<n>NeuSymEA achieves a significant 7.6% hit@1 improvement on $textDBP15K_textZH-EN$ compared with strong baselines.
  arXiv  Detail & Related papers  (2024-10-05T13:29:22Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints [46.60806942245395]
  This paper proposes a novel neural layer, LogicMP, whose layers perform mean-field variational inference over an MLN.<n>It can be plugged into any off-the-shelf neural network to encode FOLCs while retaining modularity and efficiency.<n> Empirical results in three kinds of tasks over graphs, images, and text show that LogicMP outperforms advanced competitors in both performance and efficiency.
  arXiv  Detail & Related papers  (2023-09-27T07:52:30Z)
• logLTN: Differentiable Fuzzy Logic in the Logarithm Space [11.440949097704943]
  A trend in the literature involves integrating axioms and facts in loss functions by grounding logical symbols with neural networks and fuzzy semantics. This paper presents a configuration of fuzzy operators for grounding formulas end-to-end in the logarithm space. Our findings, both formal and empirical, show that the proposed configuration outperforms the state-of-the-art.
  arXiv  Detail & Related papers  (2023-06-26T09:39:05Z)
• 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)

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.