Tag
NeSyFS is a neuro-symbolic framework for LLM agents under partial observability that uses a knowledge graph to represent belief state, combines fast/slow thinking with uncertainty-aware planning, and reflection, showing gains on ALFWorld, Webshop, and ScienceWorld.
Chronofy proposes a three-layer neuro-symbolic framework called Temporal-Logical Decay Architecture (TLDA) that integrates temporal validity directly into RAG systems via temporal subspace embeddings, decay-weighted graph retrieval, and Signal Temporal Logic verification to reduce temporal hallucination.
Proposes SAGE, a neuro-symbolic framework combining language models with cognitive models for pragmatic reasoning, demonstrated on three case studies including referential expression generation and implicatures.
This paper introduces a neuro-symbolic meta-policy for temporal knowledge-graph memory in partially observable reinforcement learning, combining RDF-based graph representations with symbolic memory management heuristics to achieve inspectable and adaptive control.
Introduces Octopus, a neuro-symbolic architecture that combines LLM swarms with algorithmic physics engines for autonomous discovery of cancer vulnerabilities, identifying IGF2 as a biomarker for drug resistance.
Proposes CART, a neuro-symbolic framework that interleaves natural language reasoning steps with symbolic constraint assertions to detect and correct errors early in chain-of-thought traces for multimodal LLMs. Reduces snowball rate from 65% to 14% and improves accuracy on multiple benchmarks.
This paper introduces a neuro-symbolic pipeline for automating LEED v4.1 BD+C compliance verification using small locally deployed language models and deterministic numeric checking. Experiments on four university buildings show that a 4B model outperforms an 8B model, and the deterministic checker corrects arithmetic errors on key credits, though multimodal inputs reduce accuracy.
This paper proposes a probabilistic extension to neuro-symbolic AGI robots using Belnap's typed intensional first-order logic. It introduces global and local symmetry transformations to preserve knowledge and enable real-time decisions, with neural networks computing probability density based on maximum information entropy.
Introduces CANDI-QA, a dataset to evaluate LLMs on contextual alignment in niche domains, comprising information assistance and applied inference questions. Systematic evaluations across ten LLMs show challenges, and a lightweight neuro-symbolic framework MTSS-Net is proposed as baseline.
This paper presents KGRL, a neuro-symbolic algorithm that uses domain knowledge expressed in Datalog to prune actions and constrain parameters in Parametrized Action Markov Decision Processes, improving sample efficiency and episodic return over state-of-the-art baselines.
This paper proposes a neuro-symbolic approach that integrates a MaxSAT oracle as a consistency validator to guide Vision-Language Models (VLMs) in solving Sudoku puzzles, improving logical consistency and the number of solved instances.
This paper proposes a theoretical framework for intelligence as atomic compression and compositional reuse, introducing the Compression Calculus and the Compounding Cascade thesis.
Introduces ZendoWorld, a controlled interactive environment for evaluating AI agents on active visual concept induction, where agents must perceive scenes, infer hidden logical rules, and design informative experiments. Experiments with various agent classes reveal that high prediction accuracy does not guarantee rule recovery, and VLM-based agents struggle with informative experimentation, highlighting gaps compared to human inductive reasoning.
RimRule proposes a neuro-symbolic method that distills compact, interpretable rules from failure traces using the Minimum Description Length principle, improving LLM tool-use performance without modifying weights, and demonstrating rule portability across models.
This paper proposes a ReAct-style agentic setup that combines LLM reasoning with verifiable feedback from SageMath, evaluating it on research-level mathematical problems. Results show substantial performance gains across models, with GPT-5.5 achieving the highest solve rate of 75.2%.
InvWeaver is a neuro-symbolic framework that uses LLMs and deductive feedback to synthesize loop invariants for programs with multiple interacting loops, outperforming existing methods on a benchmark suite.
This paper introduces Agentic SABRE, an uncertainty-aware neuro-symbolic multi-agent framework for adaptive ransomware detection that fuses semantic and behavioral evidence with Monte Carlo Dropout and interpretable risk-uncertainty triage, demonstrating improved robustness and explainability.
This paper introduces G-RRM, a neuro-symbolic approach that uses recurrent reasoning models to guide symbolic solvers for constraint satisfaction problems, showing significant speedups in certain conditions.
Nankai University and Lenovo collaborated to propose Graph of States (GoS), a neuro-symbolic framework for general abductive reasoning, which uses explicit belief states and state machines to control multi-agent collaboration, achieving significant improvements in medical diagnosis and system fault diagnosis tasks. This work was accepted at ICML 2026.
This paper presents PASE, a neuro-symbolic framework that uses LLMs to generate structured recovery plans for cloud systems and verifies them via a neural-symbolic world model, achieving over 40% reduction in recovery time.