Research

Paper

AI LLM March 24, 2026

AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection

Authors

Yangxin Yu, Yue Zhou, Bin Li, Kaiqing Lin, Haodong Li, Jiangqun Ni, Bo Cao

Abstract

The increasing realism of AI-Generated Images (AIGI) has created an urgent need for forensic tools capable of reliably distinguishing synthetic content from authentic imagery. Existing detectors are typically tailored to specific forgery artifacts--such as frequency-domain patterns or semantic inconsistencies--leading to specialized performance and, at times, conflicting judgments. To address these limitations, we present \textbf{AgentFoX}, a Large Language Model-driven framework that redefines AIGI detection as a dynamic, multi-phase analytical process. Our approach employs a quick-integration fusion mechanism guided by a curated knowledge base comprising calibrated Expert Profiles and contextual Clustering Profiles. During inference, the agent begins with high-level semantic assessment, then transitions to fine-grained, context-aware synthesis of signal-level expert evidence, resolving contradictions through structured reasoning. Instead of returning a coarse binary output, AgentFoX produces a detailed, human-readable forensic report that substantiates its verdict, enhancing interpretability and trustworthiness for real-world deployment. Beyond providing a novel detection solution, this work introduces a scalable agentic paradigm that facilitates intelligent integration of future and evolving forensic tools.

Metadata

arXiv ID: 2603.23115
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23115v1</id>\n    <title>AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection</title>\n    <updated>2026-03-24T12:10:21Z</updated>\n    <link href='https://arxiv.org/abs/2603.23115v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23115v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>The increasing realism of AI-Generated Images (AIGI) has created an urgent need for forensic tools capable of reliably distinguishing synthetic content from authentic imagery. Existing detectors are typically tailored to specific forgery artifacts--such as frequency-domain patterns or semantic inconsistencies--leading to specialized performance and, at times, conflicting judgments. To address these limitations, we present \\textbf{AgentFoX}, a Large Language Model-driven framework that redefines AIGI detection as a dynamic, multi-phase analytical process. Our approach employs a quick-integration fusion mechanism guided by a curated knowledge base comprising calibrated Expert Profiles and contextual Clustering Profiles. During inference, the agent begins with high-level semantic assessment, then transitions to fine-grained, context-aware synthesis of signal-level expert evidence, resolving contradictions through structured reasoning. Instead of returning a coarse binary output, AgentFoX produces a detailed, human-readable forensic report that substantiates its verdict, enhancing interpretability and trustworthiness for real-world deployment. Beyond providing a novel detection solution, this work introduces a scalable agentic paradigm that facilitates intelligent integration of future and evolving forensic tools.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-24T12:10:21Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Yangxin Yu</name>\n    </author>\n    <author>\n      <name>Yue Zhou</name>\n    </author>\n    <author>\n      <name>Bin Li</name>\n    </author>\n    <author>\n      <name>Kaiqing Lin</name>\n    </author>\n    <author>\n      <name>Haodong Li</name>\n    </author>\n    <author>\n      <name>Jiangqun Ni</name>\n    </author>\n    <author>\n      <name>Bo Cao</name>\n    </author>\n  </entry>"
}