A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization
Quick Answer
This paper introduces a stepwise questioning multi-agent framework to enhance long-document summarization using large language models (LLMs).
Quick Take
This paper introduces a stepwise questioning framework to enhance long-document summarization using large language models (LLMs). By employing expert and editor agents to refine summaries through targeted questioning, the method shows improved effectiveness on scientific datasets, as validated by automatic metrics.
Key Points
- Proposes a multi-agent framework for long-document summarization using LLMs.
- Utilizes expert and editor agents to refine summaries through targeted questions.
- Demonstrated effectiveness on two scientific datasets with automatic metrics.
- Addresses challenges of LLMs in summarizing documents exceeding input limits.
- Enhances the inherent capabilities of LLMs for better content summarization.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | 12 pages,3 figures,2 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.10390 [cs.CL] |
| (or arXiv:2607.10390v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.10390 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lingyun Shen [view email]
[v1]
Sat, 11 Jul 2026 16:37:06 UTC (445 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
The study evaluates three NLP approaches—Named Entity Recognition, Keyword Extraction, and Topic Modelling—using the Their Finest Hour Online Archive to automate keyword extraction from crowdsourced WWII collections. Findings suggest that while NLP methods show promise, no single approach is sufficient, and ethical considerations in automated keyword extraction are crucial for responsible stewardship.