Corrupting Ties: Investigating Robustness to Bias Injection Across Multi-Agent Network Topologies

Cléa Chataigner, Mina Arzaghi, Florian Carichon, Pablo Piantanida, Golnoosh FarnadiarXiv 2026 · arXiv

TL;DR

This paper introduces a controlled bias injection framework to audit how LLM-based multi-agent systems (MAS) propagate unfairness. By testing different network topologies, the authors demonstrate that the communication structure—not just the models themselves—is a critical factor in system-level fairness, with sequential networks proving far more vulnerable than decentralized ones.

What Problem Does This Paper Address?

As LLMs are increasingly deployed in multi-agent pipelines (e.g., an AI resume screener passing data to an AI hiring manager), a new risk emerges: bias propagation. Even if individual agents pass independent fairness audits, their interactions can amplify or spread biased information across the system.

Current auditing methods often treat AI components in isolation. This paper addresses the gap in understanding how network topology—the specific "shape" of how agents communicate—influences a system's robustness to injected bias. The authors seek to answer: How does the position of a biased agent and the overall network structure affect the final collective decision?

Methods

The authors propose a controlled bias injection framework. Unlike prior work that uses biased prompts (which models might partially ignore), this framework surgically replaces a specific agent's response at a specific round with a predefined, stereotyped biased response.

To quantify the impact, they introduce several metrics:

  • Decision Divergence (DD): Measures how frequently agents change their decisions after the injection, regardless of the direction.
  • Bias Adoption (BA): Measures whether those changes specifically move toward the injected bias.
  • System Decision Divergence (SDD): Measures how often the final "system-level" output changes.

They evaluated these metrics across five distinct topologies: Fully Connected, Mesh, Star, Chain, and Cycle.

Fig. 2. The five multi-agent network topologies considered. In the Fully Connected, each agent communicates with all other agents, whereas in the Mesh, each agent communicates with three neighbors. In the Star, a central agent (A1) exchanges information with four peripheral agents. The Chain passes information sequentially from A1 to A5, while the Cycle adds a feedback connection from A5 to A1. Fully connected and mesh networks aggregate decisions through majority voting, whereas star, chain, and cycle networks rely on a designated agent to make the final decision.

Datasets

The study utilizes three standard tabular binary classification datasets frequently used in algorithmic fairness research:

  1. Adult: Predicting if an individual's income exceeds $50,000.
  2. COMPAS: Predicting the likelihood of a defendant reoffending.
  3. Diabetes: Predicting hospital readmission within 30 days.

In all cases, gender was used as the sensitive attribute for fairness analysis. The experiments were conducted using LLMs from the Qwen and Gemma families.

Key Insights and Ideas

  • Topology as a Buffer: Decentralized networks (Fully Connected and Mesh) are significantly more robust. Because they rely on majority voting, the system can often "absorb" the bias of one or two corrupt agents without changing the final outcome.
  • Sequential Fragility: Chain and Cycle networks are the most vulnerable. In these structures, information flows one-way; a single biased injection early in the chain can cascade, leading to the highest levels of decision divergence.
  • The Centrality Risk: In Star networks, the central agent is a single point of failure. Injecting bias into the central hub has a much larger impact than injecting it into peripheral agents.
  • Four Regimes of Response: The authors identified that models don't just "obey" bias. They fall into four categories:
  • Insensitive: Robust to injection.
  • Sensitive but Undirected: The injection causes the model to flip its decision, but not necessarily toward the bias (it becomes "destabilized").
  • Bias-Adopting: The model follows the injected bias.
  • Bias-Counteracting: The model moves away from the injected bias.

Key Results

  • Sequential Impact: In Chain networks, injecting bias led to massive shifts in fairness metrics. For the Qwen3-8B model, the Change in Equal Opportunity Difference ($\Delta$EOdiff) reached as high as 0.70.
  • Star Network Influence: Injecting the central agent in a Star topology resulted in a 27% Induced Decision Divergence among peripheral agents.
  • Model Differences: Qwen3-8B was found to be highly "bias-adopting," whereas Gemma-4-26B-A4B in sequential networks often acted as "bias-counteracting," moving its decisions away from the injected stereotype.
  • Masking Effects: The authors found that aggregate fairness metrics (like group-level error rates) can sometimes hide the fact that many individual decisions have changed, highlighting the need for agent-level metrics like Decision Divergence.

Limitations and Future Work

The authors acknowledge several limitations:

  • Homogeneity: The study used networks where all five agents were the same model type. Real-world systems might use a mix of different LLMs.
  • Scale: The experiments were limited to small networks of five agents.
  • Explicit Bias: The injected bias was very explicit and stereotypical. Future work could investigate how systems handle subtler, more "natural" forms of misinformation or implicit bias.
  • Human-in-the-loop: The study focused on AI-only interactions, leaving the investigation of human-AI hybrid pipelines for future research.

Summary updated

Abstract

AI systems are increasingly deployed in high-stakes decision-making contexts, where interactions among components can introduce fairness risks that remain undetected when auditing components or collective outcomes in isolation. As LLM-based multi-agent systems become more prevalent, understanding how biased information propagates through agent interactions is essential for assessing their fairness. We introduce a controlled bias injection framework that replaces selected agent responses with predefined biased ones, enabling an intervention-based analysis of how network topology and injection configurations shape system behavior. We propose decision divergence metrics that quantify the effects of these interventions at the agent, network, and system levels, and evaluate five topologies on three binary classification tasks using LLMs from the Qwen and Gemma families. Sequential networks show the greatest divergence, whereas fully connected and mesh networks show less. Injection position also matters: in star networks, injecting the central agent has larger effects than injecting peripheral agents. Models further differ in whether divergence follows the injected bias. These findings highlight the role of network structure in the propagation of biased information and motivate topology-aware auditing of fairness risks in multi-agent systems.
BibTeX
@misc{chataigner2026corrupting,
  author = {Cléa Chataigner and Mina Arzaghi and Florian Carichon and Pablo Piantanida and Golnoosh Farnadi},
  title = {{Corrupting Ties: Investigating Robustness to Bias Injection Across Multi-Agent Network Topologies}},
  year = {2026},
  eprint = {2611.21804},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.21804},
}
Figure