A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs

• URL: http://arxiv.org/abs/2606.03867v1
• Date: Tue, 02 Jun 2026 16:39:07 GMT
• Title: A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs
• Abstract summary: Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data.<n>Existing approaches often struggle to capture complex inter-document relationships, rely heavily on large amounts of labeled data for supervised training, or exhibit limited generalization across domains and languages.<n>We present a training-free mixture-of-agents framework for MDS that leverages the complementary strengths of large language models (LLMs) and knowledge graphs.
• Score: 4.316396491271333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data. Existing approaches often struggle to capture complex inter-document relationships, rely heavily on large amounts of labeled data for supervised training, or exhibit limited generalization across domains and languages. To address these limitations, we present a training-free mixture-of-agents framework for MDS that leverages the complementary strengths of large language models (LLMs) and knowledge graphs. Our approach decomposes summarization into specialized agent tasks: extractive selection, knowledge-aware abstraction, and iterative refinement, each operating without task-specific fine-tuning. We unify their outputs using a multi-perspective consistency mechanism guided by LLMs. Experiments across four datasets in English and Vietnamese demonstrate state-of-the-art or competitive performance, validating the effectiveness and adaptability of our modular design.

Related papers

• LADLE-MM: Limited Annotation based Detector with Learned Ensembles for Multimodal Misinformation [8.769506450302154]
  LADLE-MM is a model-soup multimodal misinformation detector with Learned Ensembles for Multimodal Misinformation.<n>It is composed of two unimodal branches and a third multimodal one that enhances image and text representations.<n>It achieves competitive performance on both binary and multi-label classification tasks.
  arXiv  Detail & Related papers  (2025-12-23T11:14:58Z)
• 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)
• True Multimodal In-Context Learning Needs Attention to the Visual Context [69.63677595066012]
  Multimodal Large Language Models (MLLMs) have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks.<n>Current MLLMs tend to neglect visual cues and over-rely on textual patterns, leading to mere text imitation rather than genuine multimodal adaptation.<n>We introduce Dynamic Attention Reallocation (DARA), an efficient fine-tuning strategy that encourages models to attend to the visual context.
  arXiv  Detail & Related papers  (2025-07-21T17:08:18Z)
• Quantizing Text-attributed Graphs for Semantic-Structural Integration [6.721504414917793]
  Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains.<n>With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for graph learning.<n>We propose STAG, a novel self-supervised framework that directly quantizes graph structural information into discrete tokens using a frozen codebook.
  arXiv  Detail & Related papers  (2025-07-20T09:18:02Z)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• An Information Criterion for Controlled Disentanglement of Multimodal Data [39.601584166020274]
  Multimodal representation learning seeks to relate and decompose information inherent in multiple modalities.<n>Disentangled Self-Supervised Learning (DisentangledSSL) is a novel self-supervised approach for learning disentangled representations.
  arXiv  Detail & Related papers  (2024-10-31T14:57:31Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models [0.42832989850721054]
  Multimodal Entities Linking (MEL) is a crucial task that aims at linking ambiguous mentions within multimodal contexts to referent entities in a multimodal knowledge base, such as Wikipedia. Existing methods overcomplicate the MEL task and overlook the visual semantic information, which makes them costly and hard to scale. We propose UniMEL, a unified framework which establishes a new paradigm to process multimodal entity linking tasks using Large Language Models.
  arXiv  Detail & Related papers  (2024-07-23T03:58:08Z)
• Fine-tuning Multimodal Large Language Models for Product Bundling [53.01642741096356]
  We introduce Bundle-MLLM, a novel framework that fine-tunes large language models (LLMs) through a hybrid item tokenization approach.<n>Specifically, we integrate textual, media, and relational data into a unified tokenization, introducing a soft separation token to distinguish between textual and non-textual tokens.<n>We propose a progressive optimization strategy that fine-tunes LLMs for disentangled objectives: 1) learning bundle patterns and 2) enhancing multimodal semantic understanding specific to product bundling.
  arXiv  Detail & Related papers  (2024-07-16T13:30:14Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization [4.6493060043204535]
  We present PELMS, a pre-trained model that generates concise, fluent, and faithful summaries. We compile MultiPT, a multi-document pre-training corpus containing over 93 million documents to form more than 3 million unlabeled topic-centric document clusters. Our approach consistently outperforms competitive comparisons with respect to overall informativeness, abstractiveness, coherence, and faithfulness.
  arXiv  Detail & Related papers  (2023-11-16T12:05:23Z)

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.