NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval

2025-11-17

AI Summary

Existing RAG methods struggle to model complex inter-document semantic dependencies in multi-hop question answering, leading to path fragmentation, noise interference, and incomplete reasoning. To address this, we propose NeuroPath—the first neurobiologically inspired, two-stage semantic path tracing framework. Stage I constructs a highly coherent subgraph via goal-directed dynamic path tracing and semantic-driven node pruning. Stage II introduces intermediate-reasoning-guided secondary retrieval to complete the reasoning chain. NeuroPath automatically builds knowledge graphs using LLMs and integrates neural-inspired navigation strategies with post-retrieval augmentation. Evaluated on three multi-hop QA benchmarks, it achieves 16.3% and 13.5% absolute improvements in recall@2 and recall@5, respectively, outperforms iterative RAG in accuracy, reduces token consumption by 22.8%, and demonstrates strong robustness and scalability.

Technology Category

• Natural Language Processing: Question Answering
• Search and Optimization: Metareasoning and Metaheuristics
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Retrieval-augmented generation (RAG) greatly enhances large language models (LLMs) performance in knowledge-intensive tasks. However, naive RAG methods struggle with multi-hop question answering due to their limited capacity to capture complex dependencies across documents. Recent studies employ graph-based RAG to capture document connections. However, these approaches often result in a loss of semantic coherence and introduce irrelevant noise during node matching and subgraph construction. To address these limitations, we propose NeuroPath, an LLM-driven semantic path tracking RAG framework inspired by the path navigational planning of place cells in neurobiology. It consists of two steps: Dynamic Path Tracking and Post-retrieval Completion. Dynamic Path Tracking performs goal-directed semantic path tracking and pruning over the constructed knowledge graph (KG), improving noise reduction and semantic coherence. Post-retrieval Completion further reinforces these benefits by conducting second-stage retrieval using intermediate reasoning and the original query to refine the query goal and complete missing information in the reasoning path. NeuroPath surpasses current state-of-the-art baselines on three multi-hop QA datasets, achieving average improvements of 16.3% on recall@2 and 13.5% on recall@5 over advanced graph-based RAG methods. Moreover, compared to existing iter-based RAG methods, NeuroPath achieves higher accuracy and reduces token consumption by 22.8%. Finally, we demonstrate the robustness of NeuroPath across four smaller LLMs (Llama3.1, GLM4, Mistral0.3, and Gemma3), and further validate its scalability across tasks of varying complexity. Code is available at https://github.com/KennyCaty/NeuroPath.

Problem

• Addresses multi-hop question answering limitations in naive RAG methods
• Reduces semantic incoherence and irrelevant noise in graph-based retrieval
• Improves knowledge dependency tracking while minimizing computational overhead

Innovation

• Dynamic semantic path tracking and pruning over knowledge graphs
• Post-retrieval completion using intermediate reasoning paths
• Neurobiology-inspired framework reducing noise while maintaining coherence