AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Measuring Bias Amplification in Multi-Agent Systems with Large Language Models

Keyu Li, Jin Gao, Dequan Wang

ICLR 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent decision making

Read the paper

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies whether bias introduced by individual LLM agents is amplified through multi-step interaction in multi-agent systems, testing the hypothesis that architectural diversity helps.

Problem

Small stochastic social biases in individual LLMs can be amplified through multi-step interaction in multi-agent systems, producing skewed system-level outcomes; the abstract notes this is not yet verified for MAS architectures.

Approach

Measures bias amplification at the system level in multi-agent LLM setups and hypothesizes that architectural diversity of MAS may mitigate it; the abstract states this hypothesis is promising but unverified, so the specific mechanism is not confirmed from the abstract alone.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pass reasoning through a chain of four identical agentssequential MAS, 8 LLMs · Discrim-Eval-Openrelative GiniHurt
assign diverse personas (Doctor, Lawyer, Engineer, Merchant) to agents (ablation)sequential MAS · Discrim-Eval-Openrelative GiniNo clear effect
assign functional roles (Judger, Analyst, Reflector, Summarizer) (ablation)sequential MAS · Discrim-Eval-Openrelative GiniMixed
mix personas and functions (ablation)sequential MAS · Discrim-Eval-Openrelative GiniNo clear effect
use Spindle, Parallel or Fully-Connected topology instead of a chain (ablation)four-layer MAS · Discrim-Eval-Openrelative GiniNo clear effect
increase depth by iterating the fully-connected unit (I0 to I4) (ablation)fully-connected MAS · Discrim-Eval-Openrelative GiniHurt
mix DeepSeek-R1 and GPT-4o-mini instead of GPT-4o-mini only (ablation)fully-connected MAS · Discrim-Eval-Open (iteration 4)relative Gini: 2.0428 -> 1.4391Improved
use DeepSeek-R1 only instead of GPT-4o-mini only (ablation)fully-connected MAS · Discrim-Eval-Open (iteration 4)relative Gini: 2.0428 -> 1.2011Improved
add a neutral retrieved sentence that young people achieve innovationsequential MAS (Gemini 3.1 Pro), visa scenario · Discrim-Eval-Open (visa example)bias amplificationHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy