A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
Although large language models (LLMs) have shown promising potential in news summarization tasks, their performance on long-document summarization remains challenging as their length often exceeds the input limits. As the agent investment, which provide possibility to improve the inherent capabilities of LLMs. To enhance the effectiveness of long-document summarization based on LLMs, this paper proposes an expert-editor stepwise questioning multi-agent method, in which the expert and the editor guide another agent to refine the summary by posing questions on different aspects of the content and providing targeted clues for revision. We conducted experiments on two representative long-document scientific datasets and evaluated the results through widely recognized automatic metrics. The results demonstrated the effectiveness of our method.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 33 references that are in the map. First posted on arXiv 11 Jul 2026.
Builds on
19 of 33 references.
References · 19
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2023GPT-4 Technical Reportcited by 18,396
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
- 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
- 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
- 2023Benchmarking Large Language Models for News Summarizationcited by 445
- 2021ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 260
- 2024The Prompt Report: A Systematic Survey of Prompt Engineering Techniquescited by 121
- 2023Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarizationcited by 69
7 more
- 2024Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generationcited by 29
- 2022Toward Unifying Text Segmentation and Long Document Summarizationcited by 28
- 2025MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaborationcited by 9
- 2025Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarizationcited by 8
- 2024A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approachescited by 7
- 2024Factual Dialogue Summarization via Learning from Large Language Modelscited by 6
- 2025HERA: Improving Long Document Summarization using Large Language Models with Context Packaging and Reorderingcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs
- 2025Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization
- 2025Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing
- 2024Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
- 2026Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
- 2025NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization
- 2025Agent-as-Judge for Factual Summarization of Long Narratives
- 2025Input Order Shapes LLM Semantic Alignment in Multi-Document Summarization