# WorldFact-Bench: Beyond Image-Internal Plausibility to Image-World Consistency

arXiv: https://arxiv.org/abs/2610.11184 · HTML: https://mlsanity.com/paper/2610.11184/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [A Sanity Check for AI-generated Image Detection](https://mlsanity.com/paper/2406.19435/) (2024)
- [Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2411.15633/) (2024)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning](https://mlsanity.com/paper/2508.21048/) (2025)
- [ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization](https://mlsanity.com/paper/2505.11003/) (2025)
- [AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web](https://mlsanity.com/paper/2505.17978/) (2025)
- [MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models](https://mlsanity.com/paper/2406.11288/) (2024)
- [T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts](https://mlsanity.com/paper/2412.04300/) (2024)
- [Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.24906/) (2026)
- [UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection](https://mlsanity.com/paper/2604.21904/) (2026)
- [Multimodal Claim Extraction for Fact-Checking](https://mlsanity.com/paper/2604.16311/) (2026)

## Abstract (arXiv)

Advances in image generation have made visual authenticity increasingly difficult to assess. Although image forensics now examines both generation artifacts and higher-level visual inconsistencies, a plausible image can still contradict real-world facts or rules. We introduce WorldFact-Bench to evaluate image-world consistency from a single image, without a predefined claim or verification target. The benchmark contains 1,274 source-aligned real-fake pairs across four verification regimes and ten semantic domains. Each pair introduces a specific, evidence-supported factual conflict while seeking to preserve non-target content and visual plausibility. Images are evaluated independently, and pair accuracy requires both members of a pair to be classified correctly. We further propose PERSIST-Agent, which organizes iterative verification around a persistent state linking candidate facts, visual observations, evidence, and verification statuses. This state guides subsequent inspection and retrieval while retaining unresolved candidates. With backbone weights fixed, harness self-optimization refines the agent's prompts and execution rules through validation feedback. Experiments reveal strong label biases in several detectors and uneven gains from retrieval. On the evaluated 8B backbones, PERSIST-Agent improves pair accuracy over both direct judgment and retrieval-augmented baselines, while ablations support the role of persistent verification state. These findings highlight the value of state-guided verification and the remaining gap between visual plausibility and factual correctness.