Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection

• URL: http://arxiv.org/abs/2606.26552v1
• Date: Thu, 25 Jun 2026 02:59:33 GMT
• Title: Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection
• Abstract summary: ForeAgent is an agentic forensics framework for AI-generated image detection with iterative self-evolution.<n>ForeAgent achieves state-of-the-art performance on the Chameleon benchmark, reaching 82.18% accuracy.<n>ForeAgent produces more consistent and causally grounded reasoning compared to GPT-5 and GPT-5-mini.
• Score: 80.15317858033534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images. Although Multimodal Large Language Models (MLLMs) show strong potential for this task, existing approaches suffer from two key limitations: insufficient sensitivity to fine-grained forensic artifacts and reliance on static synthetic supervision from frontier models, leading to limited flexibility and high-cost. To address these issues, we propose ForeAgent, an agentic forensics framework for AI-generated image detection with iterative self-evolution. First, ForeAgent adopts a Perception-Verdict architecture that aggregates multi-view cues spanning semantic, spatial, and frequency-domain features, and leverages an MLLM as a verdict module to fuse these signals for a logical-grounded verdict. Second, to enable continual self-improvement, we introduce a Hindsight-Driven Self-Refining strategy following a Sampling-Reflection-Evolution paradigm. The agent performs inference rollouts on training instances. Guided by ground-truth labels as hindsight, it reflects on failure cases and low-quality reasoning trajectories to regenerate higher-quality reasoning traces. These synthesized samples are then strictly filtered through a dual-expert quality gating module. ForeAgent continuously evolves via fine-tuning on self-curated high-quality samples. Extensive experiments demonstrate that ForeAgent achieves state-of-the-art performance on the Chameleon benchmark, reaching 82.18% accuracy (+16.41% over AIDE), and achieves 93.3% mean accuracy on AIGCDetect-Benchmark across 16 generators. In addition, external evaluation shows that ForeAgent produces more consistent and causally grounded reasoning compared to GPT-5 and GPT-5-mini.

Related papers

• TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors [76.4118981404995]
  Trajectory-Injected Generative Attack (TIGA) is a source-image-free and training free framework that generates detector-evasive images.<n>TIGA steers the latent Denoising Diffusion Implicit Model (DDIM) trajectory so that adversarial properties emerge during generation.<n>TIGA achieves strong blackbox attack performance, transferability, and high robustness under common post-processing operations.
  arXiv  Detail & Related papers  (2026-07-28T15:51:39Z)
• ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors [28.44035744358622]
  This paper introduces ARMOR++, a robust multi-agent framework designed for high-transferability deepfake evasion.<n>By integrating five complementary primitives, ARMOR++ effectively targets heterogeneous inductive biases.<n> Rigorous evaluation on the AADD-2025 benchmark demonstrates that ARMOR++ significantly outperforms existing agentic and non-agentic baselines.
  arXiv  Detail & Related papers  (2026-07-16T17:45:13Z)
• Reasoning-Aware AIGC Detection via Alignment and Reinforcement [55.09684020007737]
  REVEAL is a framework that generates interpretable reasoning chains before classification.<n>It achieves state-of-the-art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-04-21T07:29:55Z)
• AgentV-RL: Scaling Reward Modeling with Agentic Verifier [63.55502685076245]
  Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS)<n>We propose Agentic Verifier, a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.<n>We show that Agentic Verifier yields consistent performance gains under both parallel and sequential TTS.
  arXiv  Detail & Related papers  (2026-04-17T12:27:36Z)
• AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning [7.129476412364631]
  We propose AnomalyAgent, an anomaly synthesis agent with self-reflection, knowledge retrieval, and iterative refinement capabilities.<n>Specifically, AnomalyAgent is equipped with five tools: Prompt Generation (PG), Image Generation (IG), Quality Evaluation (QE), Knowledge Retrieval (KR), and Mask Generation (MG)<n>On the MVTec-AD dataset, AnomalyAgent synthesis achieves IS/IC-L of 2.0.33 for anomaly generation, 57.0% classification accuracy using ResNet34, and 99.3%/74.2% AP at the image/pixel level using a simple UNet.
  arXiv  Detail & Related papers  (2026-04-09T07:17:00Z)
• EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection [19.507664662884086]
  EvoGuard is a novel agentic framework for AIGI detection.<n>It encapsulates various state-of-the-art (SOTA) off-the-shelf MLLM and non-MLLM detectors as callable tools.<n>It achieves SOTA accuracy while mitigating the bias between positive and negative samples.
  arXiv  Detail & Related papers  (2026-03-18T04:14:40Z)
• RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback [54.39884046754265]
  RetroAgent is an online RL framework that enables agents to master complex interactive environments.<n>Our experiments show that RetroAgent achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-03-09T16:23:33Z)
• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• Scaling Up AI-Generated Image Detection via Generator-Aware Prototypes [15.99138549265524]
  Generator-Aware Prototype Learning (GAPL) is a framework that constrains representation with a structured learning paradigm.<n>GAPL achieves state-of-the-art performance, showing superior detection accuracy across a wide variety of GAN and diffusion-based generators.
  arXiv  Detail & Related papers  (2025-12-15T04:58:08Z)
• From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection [19.240335260177382]
  We introduce AIFo (Agent-based Image Forensics), a training-free framework that emulates human forensic investigation through multi-agent collaboration.<n>Unlike conventional methods, our framework employs a set of forensic tools, including reverse image search, metadata extraction, pre-trained classifiers, and VLM analysis.<n>Our comprehensive evaluation spans 6,000 images and challenges real-world scenarios, including images from modern generative platforms and diverse online sources.
  arXiv  Detail & Related papers  (2025-10-31T18:36:49Z)
• SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection [63.253850875265115]
  Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples. We propose a modular acceleration system, called SUOD, to address it.
  arXiv  Detail & Related papers  (2020-03-11T00:22:50Z)

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.