arXiv Computation and Language August 27, 2026 By Rongchen Zhao, Yu Chen, Juyuan Wang, Zhouting Mo, Jianxing Yu, Wenqing Chen, Jingping Liu

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

Read the original on arXiv Computation and Language →

PonsRAG is a retrieval‑augmented generation framework designed to improve long narrative reasoning. It introduces Triple‑Layer Indexing to connect documents and eliminate cognitive islands, and Coordinated Reasoning to retrieve and integrate evidence across multiple layers. Experiments on four long‑context narrative benchmarks show PonsRAG surpasses the best baseline with an 11.56% relative accuracy gain on multi‑choice tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jun 6

Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding

arXiv:2606. 05724v1 Announce Type: cross Abstract: Long-form narrative QA requires reasoning over evolving story worlds rather than isolated passages: answers may depend on earlier goals, changing character states, social relations, causal triggers, temporal position, and later consequences.

By Qiuyu Tian, Fengyi Chen, Yiding Li, Youyong Kong, Fan Guo, Yuyao Li, Jinjing Shen, Zhijing Xie, Yiyun Luo, Xin Zhang, Yingce Xia, Zequn Liu

rag benchmarks

arXiv Computation and Language

3d ago

Evaluating Whether LLMs Can Reliably Connect the DOTs?

arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mi...

By Eftekhar Hossain, John Salvador, Santu Karmaker

llms benchmarks

arXiv AI

Jun 30

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning

arXiv:2606. 28349v1 Announce Type: cross Abstract: Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories.

By Zeju Li, Ziyang Zheng, Yizhou Zhou, Qiang Xu

rag agents benchmarks

arXiv AI

Sep 3

DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents

DocHop is a new benchmark that tests multimodal large language models on integrated chart‑context reasoning within document‑style images. The benchmark presents narrative text that imposes multi‑step compositional constraints, while charts supply the data needed to answer questions grounded in semantic reference labels. It contains 2,074 examples across six task categories, generated via a stochastic logic‑first pipeline that controls reasoning depth and visual density, and shows a large performance gap between humans (over 90% accuracy) and the best models (62.83%).

By Zhuoran Yu, Le Thien Phuc Nguyen, Jaden Park, Xinyi Gu, Zexue He, Soochahn Lee, Rogerio Feris, Yong Jae Lee

llms nlp multimodal benchmarks

arXiv AI

Sep 10

LitSeg: Narrative-Aware Document Segmentation for Literary RAG

arXiv:2605.27156v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, particularly for long-tail do...

By Ruikang Zhang, Zhanni Chen, Yiqiao Cai, Qi Su

llms rag computer-vision fine-tuning efficiency benchmarks

arXiv AI

Sep 16

Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning

arXiv:2609.16070v1 Announce Type: cross Abstract: Generative recommendation reformulates item prediction as semantic identifier generation, yet episodic content introduces a fundamentally different s...

By Chenxing Wang, Nantao Zheng, Hao Miao, Juyuan Wang, Xinke Jiang, Yuchen Fang, Aolin Li, Haijun Wu

multimodal benchmarks

One email a morning, machine-written

Related stories

Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding

Evaluating Whether LLMs Can Reliably Connect the DOTs?

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning

DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents

LitSeg: Narrative-Aware Document Segmentation for Literary RAG

Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning