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

• URL: http://arxiv.org/abs/2511.14096v1
• Date: Tue, 18 Nov 2025 03:28:23 GMT
• Title: NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
• Authors: Junchen Li, Rongzheng Wang, Yihong Huang, Qizhi Chen, Jiasheng Zhang, Shuang Liang,
• Abstract summary: NeuroPath is a semantic path tracking RAG framework inspired by the path navigational planning of place cells in neurobiology.<n>It surpasses current state-of-the-art baselines on three multi-hop QA datasets.<n>NeuroPath achieves higher accuracy and reduces token consumption by 22.8%.
• Score: 11.73701315770174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Relatron: Automating Relational Machine Learning over Relational Databases [50.94254514286021]
  We present a study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks.<n>Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and accuracy is an unreliable guide for choice architecture.
  arXiv  Detail & Related papers  (2026-02-26T02:45:22Z)
• HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG [53.30561659838455]
  Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations.<n>Retrieval-Augmented Generation (RAG) frequently overlooks structural interdependencies essential for multi-hop reasoning.<n>Help achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$times$ speedup over leading Graph-based RAG baselines.
  arXiv  Detail & Related papers  (2026-02-24T14:05:29Z)
• IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memory [33.00642870872058]
  Retrieval-augmented generation (RAG) equips large language models with reliable knowledge memory.<n>Recent research integrates graphs and hypergraphs into RAG to capture pairwise and multi-entity relations as structured links.<n>We propose IGMiRAG, a framework inspired by human intuition-guided reasoning.
  arXiv  Detail & Related papers  (2026-02-07T12:42:31Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards [48.321707628011005]
  Lookahead Tree-Based Rollouts (LATR) is a novel rollout strategy designed to explicitly promote trajectory-level diversity.<n>LATR accelerates policy learning by 131% on average and improves final pass@1 performance by 4.2%.
  arXiv  Detail & Related papers  (2025-10-28T11:12:02Z)
• Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies [53.38648279089736]
  Geminet is a lightweight and scalable ML-based TE framework that can handle changing topologies.<n>Its neural network size is only 0.04% to 7% of existing schemes.<n>When trained on large-scale topologies, Geminet consumes under 10 GiB of memory, more than eight times less than the 80-plus GiB required by HARP.
  arXiv  Detail & Related papers  (2025-06-30T09:09:50Z)
• SymRAG: Efficient Neuro-Symbolic Retrieval Through Adaptive Query Routing [8.775121469887033]
  Current Retrieval-Augmented Generation systems use uniform processing, causing inefficiency as simple queries consume resources similar to complex multi-hop tasks.<n>We present SymRAG, a framework that introduces adaptive query routing via real-time complexity and load assessment to select symbolic, neural, or hybrid pathways.
  arXiv  Detail & Related papers  (2025-06-15T22:35:43Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Graph Neural Network Enhanced Retrieval for Question Answering of LLMs [19.24603296717601]
  Existing retrieval methods divide reference documents into passages, treating them in isolation. These passages, however, are often interrelated, such as passages that are contiguous or share the same keywords. We propose a novel retrieval method, called GNN-Ret, which leverages graph neural networks (GNNs) to enhance retrieval by exploiting the relatedness between passages.
  arXiv  Detail & Related papers  (2024-06-03T17:07:46Z)
• Long-range Meta-path Search on Large-scale Heterogeneous Graphs [11.499732874909302]
  We introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS)<n>Through a sampling evaluation strategy, LMSPS conducts a specialized and effective meta-path selection, leading to retraining with only effective meta-paths, thus mitigating costs and over-smoothing.
  arXiv  Detail & Related papers  (2023-07-17T12:20:07Z)
• AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching [76.4844593082362]
  We investigate the reason why existing end-to-end networks perform poorly in challenging conditions and establish a strong baseline for remote HR measurement with architecture search (NAS) Comprehensive experiments are performed on three benchmark datasets on both intra-temporal and cross-dataset testing.
  arXiv  Detail & Related papers  (2020-04-26T05:43:21Z)

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.