# NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

arXiv: https://arxiv.org/abs/2602.15353 · HTML: https://mlsanity.com/paper/2602.15353/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 74 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 24 of 24)

- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks](https://mlsanity.com/paper/2203.09168/) (2022)
- [UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph](https://mlsanity.com/paper/2212.00959/) (2022)
- [Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering](https://mlsanity.com/paper/2202.13296/) (2022)
- [Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.20724/) (2024)
- [Sequence-to-Sequence Knowledge Graph Completion and Question Answering](https://mlsanity.com/paper/2203.10321/) (2022)
- [Interpretable Contrastive Monte Carlo Tree Search Reasoning](https://mlsanity.com/paper/2410.01707/) (2024)
- [ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning](https://mlsanity.com/paper/2410.02052/) (2024)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbots](https://mlsanity.com/paper/2302.06466/) (2023)
- [NeuPSL: Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2205.14268/) (2022)
- [RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards](https://mlsanity.com/paper/2410.13509/) (2024)
- [Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models](https://mlsanity.com/paper/2402.15131/) (2024)
- [Graph Neural Networks for Multi-Robot Active Information Acquisition](https://mlsanity.com/paper/2209.12091/) (2022)
- [Improving Discrete Optimisation Via Decoupled Straight-Through Estimator](https://mlsanity.com/paper/2410.13331/) (2024)
- [Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data](https://mlsanity.com/paper/2405.09817/) (2024)
- [Bayesian Entropy Neural Networks for Physics-Aware Prediction](https://mlsanity.com/paper/2407.01015/) (2024)
- [FREESON: Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS](https://mlsanity.com/paper/2505.16409/) (2025)
- [Uncertainty-Aware Relational Graph Neural Network for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2403.04521/) (2024)
- [Efficient Human-in-the-Loop Active Learning: A Novel Framework for Data Labeling in AI Systems](https://mlsanity.com/paper/2501.00277/) (2024)

## Built on by (most cited first, 3 of 3)

- [Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS](https://mlsanity.com/paper/2604.10734/) (2026)
- [CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts](https://mlsanity.com/paper/2606.31986/) (2026)
- [HGSQ: Heatmap-Guided Sparse Query Detector for Real-Time Aerial Small Object Detection](https://mlsanity.com/paper/2609.13306/) (2026)

## Abstract (arXiv)

Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowledge-intensive queries that require precise, structured multi-hop inference. Knowledge graphs provide a compact symbolic substrate for factual grounding, but integrating graph structure with neural models is nontrivial: naively embedding graph facts into prompts leads to inefficiency and fragility, while purely symbolic or search-heavy approaches can be costly in retrievals and lack gradient-based refinement. We introduce NeuroSymActive, a modular framework that combines a differentiable neural-symbolic reasoning layer with an active, value-guided exploration controller for Knowledge Graph Question Answering. The method couples soft-unification style symbolic modules with a neural path evaluator and a Monte-Carlo style exploration policy that prioritizes high-value path expansions. Empirical results on standard KGQA benchmarks show that NeuroSymActive attains strong answer accuracy while reducing the number of expensive graph lookups and model calls compared to common retrieval-augmented baselines.