Metraipolis › archive › dc_746e6837c39b

FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detection — arXiv:2609.05876

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05876
License (as archived)
CC0-1.0
Archived
2026-10-16T15:06:39.196Z
SHA-256 of the archived text
4e3b0038488c1bef9141630843395635354c8ea5cd76c45bf8412bef47065414
Stable URL of this page
https://metraipolis.com/documento/dc_746e6837c39b

How to cite

FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detection — arXiv:2609.05876 — arXiv (en), https://arxiv.org/abs/2609.05876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_746e6837c39b (Metraipolis archive dc_746e6837c39b, sha256 4e3b0038488c1bef9141630843395635354c8ea5cd76c45bf8412bef47065414)
BibTeX
@misc{dc746e6837c39b,
  title = {FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detection — arXiv:2609.05876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_746e6837c39b; sha256 4e3b0038488c1bef9141630843395635354c8ea5cd76c45bf8412bef47065414},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI-generated image detection is increasingly open-world: new image generators produce highly realistic images that make visual artifacts harder to identify. Existing detectors usually rely on a fixed set of forensic cues, so a detector that works well for one generator family may fail on another. We introduce FACT (Forensic Agent with Compiled Tool-use Trajectories), which learns an image-conditioned tool-use policy for forensic analysis. Instead of applying a fixed detector, FACT decides which forensic tools to call, interprets the returned evidence, and stops when sufficient evidence has been collected. FACT follows an Evolve--Distill--Refine pipeline: it evolves an execution-verified forensic skill, compiles the skill into action--observation tool-use trajectories, distills them into a compact agent, and refines the policy with cost-aware GRPO. Across two internal and four public benchmarks, FACT achieves the best performance among all compared methods, including on recent unseen generators, deepfakes, and manipulated images.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05876 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T14:49:57.009Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).