Competing Influence in LLM Populations: Budget Timing and Baseline Drift
physics.soc-ph, cs.CL, cs.MA
Submitted: 2026-11-09
Updated: 2026-11-09
License: http://creativecommons.org/licenses/by/4.0/
The gist: When competing campaigns target a population of large language model (LLM) agents, observed opinion changes may reflect both campaign influence and changes that would occur without intervention.
Terminology
Abstract
When competing campaigns target a population of large language model (LLM) agents, observed opinion changes may reflect both campaign influence and changes that would occur without intervention. We study how the timing of campaign expenditure and the population's own evolution shape outcomes in a network of persona-conditioned LLM agents that exchange and revise opinions in natural language. A proponent and a challenger are tasked with generating opposing messages under equal delivery budgets, while a separate stance probe measures opinions without influencing the simulation. Across eight claims, we compare single-campaign and competitive conditions against matched no-campaign runs, and evaluate all nine combinations of early, sustained, and late spending on a reference topic. Baseline stance drift varies substantially across claims and, on some, accounts for a sizeable fraction of apparent campaign effects. After accounting for this drift, the direction of observed campaign-associated changes aligns more closely with the claim's epistemic standing than with the campaigner's assigned role. Uninfluenced populations also consistently lose stance diversity, demonstrating that directional opinion change and convergence are distinct phenomena. In networks with two opinion-segregated communities, campaigns primarily reduce differences between communities rather than diversity within them. LLM campaign agents do not always argue for their assigned positions, particularly when these conflict with established evidence. Finally, campaign outcomes depend on the opponent's expenditure schedule: unlike a matched numerical bounded-confidence population receiving interventions at the same times and locations, the LLM population exhibits a payoff structure with no pure-strategy equilibrium.
Sources
- The Effect of Network Topology on the Equilibria of Influence-Opinion Games
- Agent-based simulation of online social networks and disinformation
- Language-Driven Opinion Dynamics in Agent-Based Simulations with LLMs
- DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents
- Opinion dynamics and mutual influence with LLM agents through dialog simulation
- You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation
- Characterizing Opinion Evolution of Networked LLMs
- Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation
- Opinion Polarization in LLM-Based Social Networks: Manipulation and Mitigation
Related papers
- Transient Signal Propagation in Heterogeneous Networks under Various Inputs
- Phase Transitions in Economic Inequality:Taxation and Extremal Replacement Dynamics
- New rules, old habits: across seven team sports, each league keeps its own way of using the rules
- URBAN-SPIN: A street-level bikeability index to inform design implementations in historical city centres
- Logarithmic dispersion at marginal stability in collective attention
- Glassy dynamics of metropolitan human mobility frozen near the gravitational equilibrium