cs.AINov 16, 2026

Language-model agents' beliefs can be manipulated via truthful evidence in open channel

Authors: Jinwei Hu, Qisong He, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang

Organizations: School of Computer Science and Informatics, University of Liverpool, Liverpool, UK · Department of Computer Science, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

Abstract

Language-model agents' beliefs can be manipulated through open channels such as social media, even when the information they receive is truthful. When agents fill gaps between fragments with self-induced relationships, they may accept those relationships as established facts and pass the resulting rumours to others. Drawing on cognitive theory of narrative understanding and film theory of montage, we introduce Generative Montage to operationalize this failure, termed narrative overfitting, by coordinating agents to arrange truthful fragments into misleading narratives. Across 1,090 rumour targets from six Twitter events, agents often accepted rumours overconfidently, with overall acceptance exceeding 65 percent in twelve of fourteen models. Acceptance remained above 50 percent after majority voting or review of the same evidence, showing how errors can reach downstream decisions. To explain this susceptibility, fragment interventions identify posts that influence belief within complete narratives. Synthetic controls then show that similar response patterns arise from valid evidence, separating belief influence from evidential support. This distinction motivates Grounded Monitor, a proof-of-concept neuro-symbolic runtime monitor that checks direct evidential support to guide agents' judgements, improving decision accuracy by 5.6 to 29.0 percentage points across original and anonymized settings. These findings expose a cognitive route to rumour amplification and support monitoring inferred relationships before agent-generated conclusions guide public decisions.

Figures & tables

Explore similar work

CardsList
  1. Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions

    Oct 15, 2026Liangjie Huang, Henry Peng Zou, Wei-Chieh Huang +3Multi-Agent LLM SystemsLLM Agent Reliability

  2. The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents

    Oct 17, 2026Jinwei Hu, Youcheng Sun, Yi Dong +1Adversarial Attacks on LLMsLLM Agent Reliability