A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization

• URL: http://arxiv.org/abs/2607.10390v1
• Date: Sat, 11 Jul 2026 16:37:06 GMT
• Title: A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization
• Abstract summary: Large language models (LLMs) have shown promising potential in news summarization tasks.<n>This paper proposes an expert-editor stepwise questioning multi-agent method to enhance the effectiveness of long-document summarization.
• Score: 0.3580891736370874
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems [59.20800753428596]
  We present MAS-ProVe, a systematic empirical study of process verification for multi-agent systems (MAS)<n>Our study spans three verification paradigms (LLM-as-a-Judge, reward models, and process reward models)<n>We find that process-level verification does not consistently improve performance and frequently exhibits high variance.
  arXiv  Detail & Related papers  (2026-02-03T03:30:36Z)
• LongDA: Benchmarking LLM Agents for Long-Document Data Analysis [55.32211515932351]
  LongDA targets real-world settings in which navigating long documentation and complex data is the primary bottleneck.<n>LongTA is a tool-augmented agent framework that enables document access, retrieval, and code execution.<n>Our experiments reveal substantial performance gaps even among state-of-the-art models.
  arXiv  Detail & Related papers  (2026-01-05T23:23:16Z)
• Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization [86.98098988779809]
  We propose SummQ, a novel adversarial multi-agent framework for long document summarization.<n>Our approach employs summary generators and reviewers that work collaboratively to create and evaluate comprehensive summaries.<n>We evaluate SummQ on three widely used long document summarization benchmarks.
  arXiv  Detail & Related papers  (2025-09-25T08:36:19Z)
• Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization [49.61589046694085]
  We propose a topic-guided reinforcement learning approach to improve content selection in Multi-Document Summarization.<n>We first show that explicitly prompting models with topic labels enhances the informativeness of the generated summaries.
  arXiv  Detail & Related papers  (2025-09-11T21:01:54Z)
• LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents [3.887688898850802]
  We present a structured prompting methodology as a viable alternative to the often expensive fine-tuning.<n>We tack long legal documents from the CUAD dataset on the task of information retrieval.<n>We tackle the resulting candidate selection problem with the introduction of the Distribution-based Localisation and Inverse Cardinality Weightings.
  arXiv  Detail & Related papers  (2025-09-02T12:09:49Z)
• MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance [5.192956837901584]
  We introduce MDBench, a new dataset for evaluating large language mod-els (LLMs) on the task of multi-document reasoning.<n>We use a novel synthetic generation process, allowing us to controllably and efficiently generate challenging document sets.<n>We analyze the behavior of popular LLMs and prompting techniques, finding that MDBENCH poses significant challenges for all methods.
  arXiv  Detail & Related papers  (2025-06-17T19:14:30Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing [43.75154489681047]
  We propose a novel framework leveraging test-time scaling for Multi-Document Summarization (MDS)<n>Our approach employs prompt ensemble techniques to generate multiple candidate summaries using various prompts, then combines them with an aggregator to produce a refined summary.<n>To evaluate our method effectively, we also introduce two new LLM-based metrics: the Consistency-Aware Preference (CAP) score and LLM Atom-Content-Unit (LLM-ACU) score.
  arXiv  Detail & Related papers  (2025-02-27T23:34:47Z)
• Large Multimodal Agents: A Survey [78.81459893884737]
  Large language models (LLMs) have achieved superior performance in powering text-based AI agents. There is an emerging research trend focused on extending these LLM-powered AI agents into the multimodal domain. This review aims to provide valuable insights and guidelines for future research in this rapidly evolving field.
  arXiv  Detail & Related papers  (2024-02-23T06:04:23Z)

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.