Persuasion Propagation: Does Persuasion Change AI Agent Behavior?
cs.AI, cs.MA
Submitted: 2026-01-31
Updated: 2026-10-07
Comments: Code available at https://github.com/HyejunJeong/persuasion-propagation
Code: https://github.com/HyejunJeong/persuasion-propagation
License: http://creativecommons.org/licenses/by/4.0/
The gist: AI agents combine normal conversation with autonomous task execution, allowing earlier context to shape how later tasks are executed.
Terminology
Abstract
AI agents combine normal conversation with autonomous task execution, allowing earlier context to shape how later tasks are executed. Yet studying this possibility is challenging because agent behavior is noisy and costly to reproduce, and observed behavioral changes can be difficult to separate from generic context sensitivity. We first ask whether task-irrelevant persuasion changes how agents act, a phenomenon we call persuasion propagation, and whether persuasion susceptibility explains variation in these effects. We show that persuasive interaction leaves a measurable, task-dependent behavioral footprint on downstream agent execution. In web research, it increases execution time by 56% and domains visited by 16.3% relative to a baseline, while coding shows faster execution with larger revisions. However, agents that are more susceptible to persuasive conversational context do not reliably predict the magnitude of the downstream behavioral shifts. This motivates behavior-level evaluation of persuasion in AI agents.
Sources
- AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- MillStone: How Open-Minded Are LLMs?
- Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
- Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
- ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
- CORE: Full-Path Evaluation of LLM Agents Beyond Final State
- TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
- Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure
- Accumulating Context Changes the Beliefs of Language Models
- Making Retrieval-Augmented Language Models Robust to Irrelevant Context
- Towards Strategic Persuasion with Language Models
- Must Read: A Comprehensive Survey of Computational Persuasion
- LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
- When Large Language Models are More PersuasiveThan Incentivized Humans, and Why
- A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies
- AI persuading AI vs AI persuading Humans: LLMs' Differential Effectiveness in Promoting Pro-Environmental Behavior
- Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
- The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
- KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems