NoveltyAgent: Autonomous Novelty Reporting Agent with Point-wise Novelty Analysis and Self-Validation

TL;DR

NoveltyAgent is a multi-agent system that automates detailed novelty assessment of academic papers through fine-grained analysis and self-validation, significantly improving the quality and reliability of novelty reporting.

Contribution

It introduces a novel multi-agent framework with point-wise novelty analysis and a self-validation mechanism, advancing automated novelty evaluation in academic research.

Findings

Achieves state-of-the-art performance, outperforming GPT-5 DeepResearch by 10.15%.

Provides a comprehensive, faithful novelty report generation.

Establishes a checklist-based evaluation framework for open-ended tasks.

Abstract

The exponential growth of academic publications has led to a surge in papers of varying quality, increasing the cost of paper screening. Current approaches either use novelty assessment within general AI Reviewers or repurpose DeepResearch, which lacks domain-specific mechanisms and thus delivers lower-quality results. To bridge this gap, we introduce NoveltyAgent, a multi-agent system designed to generate comprehensive and faithful novelty reports, enabling thorough evaluation of a paper's originality. It decomposes manuscripts into discrete novelty points for fine-grained retrieval and comparison, and builds a comprehensive related-paper database while cross-referencing claims to ensure faithfulness. Furthermore, to address the challenge of evaluating such open-ended generation tasks, we propose a checklist-based evaluation framework, providing an unbiased paradigm for building reliable evaluations. Extensive experiments show that NoveltyAgent achieves state-of-the-art performance, outperforming GPT-5 DeepResearch by 10.15%. We hope this system will provide reliable, high-quality novelty analysis and help researchers quickly identify novel papers. Code and demo are available at https://github.com/SStan1/NoveltyAgent.