Belief Cascades Drive Persuasion in LLM Agent Networks
cs.CL, cs.AI
Submitted: 2026-08-25
Updated: 2026-08-25
License: http://creativecommons.org/licenses/by/4.0/
The gist: Multi-agent LLM systems increasingly debate answers, coordinate research, simulate users, and mediate information flows, making agent-to-agent persuasion a basic but undermeasured capability.
Terminology
Abstract
Multi-agent LLM systems increasingly debate answers, coordinate research, simulate users, and mediate information flows, making agent-to-agent persuasion a basic but undermeasured capability. We introduce a controlled testbed for studying how goal-directed persuaders shift elicited stances in networks of LLM agents grounded in real-world ego-network topologies. Across four LLM backbones, five graphs, and 55 policy statements, we find that persuasion dynamics depend on the interaction between topology, competition, topic, and model prior. Additionally, we show that direct exposure reliably predicts next-round stance change in competing runs, and peer relays carry smaller but measurable influence, showing that agents not assigned to persuade can still transmit persuasive force. Finally, analyzing post text alone misses important movement: planned strategies are only partly realized in executed messages, action choices can diverge from message content, and persuadees rarely state the stance shifts detected by probes. These results argue for evaluating multi-agent persuasion as a trajectory- and exposure-level process, using belief probes, exposure provenance, and action logs to identify who influenced whom and whether visible language reflects underlying stance movement.
Sources
- Political Ideology Shifts in Large Language Models
- Measuring Implicit Bias in Explicitly Unbiased Large Language Models
- Artificial Influence: An Analysis Of AI-Driven Persuasion
- Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments
- Language-Driven Opinion Dynamics in Agent-Based Simulations with LLMs
- A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies
- Towards Strategic Persuasion with Language Models
- Accumulating Context Changes the Beliefs of Language Models
- Machine Generated Product Advertisements: Benchmarking LLMs Against Human Performance
- Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory
- Large Language Model Driven Agents for Simulating Echo Chamber Formation
- MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook
- Evidence of a log scaling law for political persuasion with large language models
- ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind
- Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
- S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents
- Large Language Models as Misleading Assistants in Conversation
- AgentSims: An Open-Source Sandbox for Large Language Model Evaluation
- "Humans welcome to observe": A First Look at the Agent Social Network Moltbook
- LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering