Belief Cascades Drive Persuasion in LLM Agent Networks

• URL: http://arxiv.org/abs/2608.25152v1
• Date: Tue, 25 Aug 2026 21:01:19 GMT
• Title: Belief Cascades Drive Persuasion in LLM Agent Networks
• Abstract summary: We study how goal-directed persuaders shift elicited stances in networks of LLM agents grounded in real-world ego-network topologies.<n>We show that direct exposure reliably predicts next-round stance change in competing runs, and peer relays carry smaller but measurable influence.<n>These results argue for evaluating multi-agent persuasion as a trajectory- and exposure-level process.
• Score: 71.17605142402785
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions [66.7908338529737]
  Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern.<n>Existing testbeds are text-only and run on a single fixed agent configuration, missing the non-verbal sensorimotor channels treated as core by deception.<n>We introduce MineAmongUs, a 3D multimodal Among Us sandbox where imposter agents must deceive crewmates through joint verbal and non-verbal action.
  arXiv  Detail & Related papers  (2026-08-31T08:24:29Z)
• A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing [16.188738760148645]
  PERSUASIONTRACE is a framework for studying persuasion in human-LLM interaction.<n>It records multi-turn belief reports from human or simulated targets of persuasion.<n>It annotates persuader turns with rhetorical dimensions and evaluates simulators by fidelity to real human belief dynamics.
  arXiv  Detail & Related papers  (2026-06-03T18:17:20Z)
• Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts [3.473277059746767]
  We investigate whether prompt-as-action can be parameterized so as to construct a lightweight policy.<n>We evaluate the dialogue flow based on five indicators: responsiveness, rebuttal, evidence usage, non-repetition, and stance shift.
  arXiv  Detail & Related papers  (2026-03-10T16:47:25Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• DEBATE: A Large-Scale Benchmark for Role-Playing LLM Agents in Multi-Agent, Long-Form Debates [10.609797175227644]
  We introduce DEBATE, the first large-scale empirical benchmark to evaluate the authenticity of the interaction between multi-agent role-playing LLMs.<n>We systematically evaluate and identify critical discrepancies between simulated and authentic group dynamics.
  arXiv  Detail & Related papers  (2025-10-29T02:21:10Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems [90.96738882568224]
  This paper investigates the over-competition in multi-agent debate, where agents under extreme pressure exhibit unreliable, harmful behaviors.<n>To study this phenomenon, we propose HATE, a novel experimental framework that simulates debates under a zero-sum competition arena.
  arXiv  Detail & Related papers  (2025-09-30T11:44:47Z)
• Persuasion with Large Language Models: a Survey [49.86930318312291]
  Large Language Models (LLMs) have created new disruptive possibilities for persuasive communication. In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness. Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks.
  arXiv  Detail & Related papers  (2024-11-11T10:05:52Z)
• Persuasion Games using Large Language Models [0.0]
  Large Language Models (LLMs) have emerged as formidable instruments capable of comprehending and producing human-like text. This paper explores the potential of LLMs, to shape user perspectives and subsequently influence their decisions on particular tasks. This capability finds applications in diverse domains such as Investment, Credit cards and Insurance.
  arXiv  Detail & Related papers  (2024-08-28T15:50:41Z)
• Stance Detection with Collaborative Role-Infused LLM-Based Agents [39.75103353173015]
  Stance detection is vital for content analysis in web and social media research. However, stance detection requires advanced reasoning to infer authors' implicit viewpoints. We design a three-stage framework in which LLMs are designated distinct roles. We achieve state-of-the-art performance across multiple datasets.
  arXiv  Detail & Related papers  (2023-10-16T14:46:52Z)

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.