PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning

arXiv:2608.25486v1 Announce Type: cross Abstract: Long Narrative Reasoning is an essential capability for processing and reasoning over complex narratives. While retrieval-augmented generation provides a promising framework, existing methods still face two critical challenges: cognitive islanding and cross-layer evidence disconnection. To address these issues, we propose PonsRAG, a coordinated RAG framework inspired by the biological pons. PonsRAG consists of two key components: Triple-Layer Indexing, which organizes documents into a connected knowledge structure to bridge cognitive islands, and Coordinated Reasoning, which retrieves evidence across distinct layers and integrates cross-layer information into a unified context. We evaluate PonsRAG on four long-context narrative benchmarks, and experimental results show that it outperforms the strongest baseline, achieving a 11.56% relative improvement in average accuracy on multi-choice tasks.

Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation
Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG

Source: arXiv cs.CL | 2026-08-27

Related