Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Juntai, Zhang, Xiang, Li, Raymond, Li, Chuyuan, You, Chenyu, Joty, Shafiq, Carenini, Giuseppe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916744924233728
author Cao, Juntai
Zhang, Xiang
Li, Raymond
Li, Chuyuan
You, Chenyu
Joty, Shafiq
Carenini, Giuseppe
author_facet Cao, Juntai
Zhang, Xiang
Li, Raymond
Li, Chuyuan
You, Chenyu
Joty, Shafiq
Carenini, Giuseppe
contents Recent advances in test-time scaling have shown promising results in improving Large Language Model (LLM) performance through strategic computation allocation during inference. While this approach has demonstrated strong improvements in logical and mathematical reasoning tasks, its application to natural language generation (NLG), particularly summarization, remains unexplored. Multi-Document Summarization (MDS), a fundamental task in NLG, presents unique challenges by requiring models to extract and synthesize essential information across multiple lengthy documents. Unlike reasoning tasks, MDS demands a more nuanced approach to prompt design and ensemble methods, as no single "best" prompt can satisfy diverse summarization requirements. We propose a novel framework leveraging test-time scaling for MDS. 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. 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, which assess summary quality while addressing the positional bias inherent in traditional automatic evaluation. Our extensive experiments demonstrate that this framework significantly enhances summary quality while also revealing the practical scaling boundaries to MDS tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20592
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing
Cao, Juntai
Zhang, Xiang
Li, Raymond
Li, Chuyuan
You, Chenyu
Joty, Shafiq
Carenini, Giuseppe
Computation and Language
Recent advances in test-time scaling have shown promising results in improving Large Language Model (LLM) performance through strategic computation allocation during inference. While this approach has demonstrated strong improvements in logical and mathematical reasoning tasks, its application to natural language generation (NLG), particularly summarization, remains unexplored. Multi-Document Summarization (MDS), a fundamental task in NLG, presents unique challenges by requiring models to extract and synthesize essential information across multiple lengthy documents. Unlike reasoning tasks, MDS demands a more nuanced approach to prompt design and ensemble methods, as no single "best" prompt can satisfy diverse summarization requirements. We propose a novel framework leveraging test-time scaling for MDS. 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. 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, which assess summary quality while addressing the positional bias inherent in traditional automatic evaluation. Our extensive experiments demonstrate that this framework significantly enhances summary quality while also revealing the practical scaling boundaries to MDS tasks.
title Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing
topic Computation and Language
url https://arxiv.org/abs/2502.20592