# The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents

arXiv: https://arxiv.org/abs/2410.19064 · HTML: https://mlsanity.com/paper/2410.19064/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 13 of 13)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [The science of fake news](https://mlsanity.com/paper/2307.07903/) (2023)
- [Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks](https://mlsanity.com/paper/2310.10830/) (2023)
- [From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake News](https://mlsanity.com/paper/2403.09498/) (2024)
- [It's about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits](https://mlsanity.com/paper/2302.03147/) (2023)
- [Improving the Robustness of Summarization Systems with Dual Augmentation](https://mlsanity.com/paper/2306.01090/) (2023)
- [Balancing Information Exposure in Social Networks](https://mlsanity.com/paper/1709.01491/) (2017)
- [A Topic-aware Summarization Framework with Different Modal Side Information](https://mlsanity.com/paper/2305.11503/) (2023)
- [How does Truth Evolve into Fake News? An Empirical Study of Fake News Evolution](https://mlsanity.com/paper/2103.05944/) (2021)
- [Mechanisms of True and False Rumor Sharing in Social Media: Collective Intelligence or Herd Behavior?](https://mlsanity.com/paper/2207.03020/) (2022)
- [The Evolution of Rumors on a Closed Platform during COVID-19](https://mlsanity.com/paper/2104.13816/) (2021)

## Built on by (most cited first, 24 of 24)

- [Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations](https://mlsanity.com/paper/2504.03274/) (2025)
- [Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents](https://mlsanity.com/paper/2502.13012/) (2025)
- [Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models](https://mlsanity.com/paper/2505.15406/) (2025)
- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains](https://mlsanity.com/paper/2504.20199/) (2025)
- [Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies](https://mlsanity.com/paper/2510.11389/) (2025)
- [BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking](https://mlsanity.com/paper/2502.16181/) (2025)
- [A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation Detection](https://mlsanity.com/paper/2503.23329/) (2025)
- [Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement](https://mlsanity.com/paper/2502.17442/) (2024)
- [The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence](https://mlsanity.com/paper/2601.05478/) (2026)
- [What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews](https://mlsanity.com/paper/2601.05563/) (2026)
- [How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?](https://mlsanity.com/paper/2602.18464/) (2026)
- [Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy](https://mlsanity.com/paper/2603.06801/) (2026)
- [You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation](https://mlsanity.com/paper/2605.17353/) (2026)
- [Detecting AI-Generated Video: A Vision-Language Dual-View Survey](https://mlsanity.com/paper/2607.10787/) (2026)
- [Large language models for spreading dynamics in complex systems](https://mlsanity.com/paper/2602.08085/) (2026)
- [LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News Detection](https://mlsanity.com/paper/2603.19293/) (2026)
- [Latent Causal Void: Explicit Missing-Context Reconstruction for Misinformation Detection](https://mlsanity.com/paper/2605.12156/) (2026)
- [AI-Model Network: Concept, Current State and Future](https://mlsanity.com/paper/2606.27382/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)
- [LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems](https://mlsanity.com/paper/2608.26849/) (2026)
- [LLMs for Social Network Modeling: From Network Generation to Dynamic Processes](https://mlsanity.com/paper/2609.08049/) (2026)
- [VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation](https://mlsanity.com/paper/2609.35028/) (2026)
- [SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys](https://mlsanity.com/paper/2609.35250/) (2026)

## Abstract (arXiv)

With the growing spread of misinformation online, understanding how true news evolves into fake news has become crucial for early detection and prevention. However, previous research has often assumed fake news inherently exists rather than exploring its gradual formation. To address this gap, we propose FUSE (Fake news evolUtion Simulation framEwork), a novel Large Language Model (LLM)-based simulation approach explicitly focusing on fake news evolution from real news. Our framework model a social network with four distinct types of LLM agents commonly observed in daily interactions: spreaders who propagate information, commentators who provide interpretations, verifiers who fact-check, and bystanders who observe passively to simulate realistic daily interactions that progressively distort true news. To quantify these gradual distortions, we develop FUSE-EVAL, a comprehensive evaluation framework measuring truth deviation along multiple linguistic and semantic dimensions. Results show that FUSE effectively captures fake news evolution patterns and accurately reproduces known fake news, aligning closely with human evaluations. Experiments demonstrate that FUSE accurately reproduces known fake news evolution scenarios, aligns closely with human judgment, and highlights the importance of timely intervention at early stages. Our framework is extensible, enabling future research on broader scenarios of fake news.