mlsanityData to 14 Oct 2026

Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric

arXiv 2609.18306 ↗First posted 16 Sep 2026cs.LGcited by 0

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Large language models (LLMs) are increasingly deployed in applications involving interaction between agents, where their output plays a role in collective reasoning and decision-making processes. Despite significant research into the functioning of LLMs in such multi-agent systems, the processes of bias propagation in such systems are still a challenge. This work studies how biased opinions are propagated in the form of textual interaction in an environment of LLMs, in which a minority of agents maintain persistent extreme opinions, while the remaining agents iteratively update their beliefs through structured textual interactions. The findings show that even the presence of a small percentage of biased agents in such a system leads to significant shifts in the opinions of non-biased agents. It suggests that for the same percentage of biased agents, the shifts occur more quickly for the Llama~3.2 model when compared to a classical Friedkin-Johnsen (FJ) model. Further semantic analysis demonstrates that rhetorical consistency in textual explanations increases systematically with biased exposure and, importantly, is partially decoupled from numerical convergenumericalutral agents adopt the vocabulary employed by the biased agents even in configurations where their numerical opinion shifts remain moderate. The research helps explain how bias and language develop together in multi-agent language model ecosystems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 8 of its 19 references that are in the map. First posted on arXiv 16 Sep 2026.

Builds on

8 of 19 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Towards Simulating Social Influence Dynamics with LLM-based Multi-agents30 Jul
  2. 2024Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions3 Oct
  3. 2024Social Opinions Prediction Utilizes Fusing Dynamics Equation with LLM-based Agents13 Sep
  4. 2023Simulating Opinion Dynamics with Networks of LLM-based Agents16 Nov

Other references · 4

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  2. 2024Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networkscited by 33
  3. 2025Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systemscited by 8
  4. 2025MTOS: A LLM-Driven Multi-topic Opinion Simulation Framework for Exploring Echo Chamber Dynamicscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025An Empirical Study of Group Conformity in Multi-Agent Systems
  2. 2025The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
  3. 2025Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models
  4. 2024On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models
  5. 2025Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation
  6. 2025Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
  7. 2025Persuasiveness and Bias in LLM: Investigating the Impact of Persuasiveness and Reinforcement of Bias in Language Models
  8. 2025Revealing Political Bias in LLMs through Structured Multi-Agent Debate