cs.CRNov 3, 2026

When Debate Amplifies Risk: Social-Bias Vulnerabilities in Multi-Agent Safety Deliberation

Authors: Qinghua Mao, Xi Lin, Yuxin Qi, Zihao Xu, Jinze Gu, Yuliang Chen

Organizations: Shanghai Jiao Tong University, Shanghai, China · China Telecom, Shanghai, China

Abstract

Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynamics. When retrieved Web sources contain latent hazards alongside safe factual content, social biases such as conformity pressure and authority deference can override evidence-grounded safety boundaries. In this work, we investigate whether the social structure of deliberation can paradoxically amplify latent Web safety risks. We introduce SafeConflict-Bias, a controlled counterfactual diagnostic protocol spanning six core Web risk categories, which holds queries and retrieved evidence strictly invariant while isolating conversational majority sway, authority cues, and confidence asymmetry. Empirical evaluation across diverse proprietary and open-source backbones reveals that while isolated models reliably reject unsafe guidance, standard MAD catastrophically capitulates to social pressure---surging unsafe adoption from 0.0% up to 100.0% and systematically silencing safe minority evidence. To resolve this systemic fragility without retraining or debate regeneration, we propose RiskTrace-Debias, an inference-time auditing framework uniting evidence-first precommitment, social-metadata masking, and consistency-gated arbitration. RiskTrace-Debias suppresses worst-case unsafe adoption to ≤2.0%\le 2.0\% across all architectures without inducing over-refusal, while generating verifiable provenance traces to audit interpersonal manipulation in Web deliberation.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 9, 2026

From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation

Multi-agent debate improves LLM reasoning, yet agreement is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus stopping commits that error to automated action with no recourse. We introduce Conformal Social Choice, a post-hoc layer that converts debate outputs into calibrated act-versus-escalate decisions. Verbalized probability distributions from heterogeneous agents are aggregated via a linear opinion pool and calibrated with split conformal prediction, yielding fixed-round marginal coverage: at any pre-specified round, the correct answer is included with probability ≥ 1−α{\geq}\,1{-}α, without assumptions on individual model calibration. A hierarchical action policy maps singletons to autonomous action and larger sets to human escalation. Across eight MMLU-Pro domains and two additional benchmarks, fixed-round coverage stays close to target. The key finding is not that debate becomes more accurate, but that the conformal layer makes its failures actionable: at the final round, 81.9% of wrong-consensus cases are flagged by non-singleton sets at α=0.05α{=}0.05. Separately, among cases that reach a singleton before the final round, accuracy reaches 90.0--96.8% on MMLU-Pro (up to 22.1pp above consensus stopping): a selection effect, not a reasoning improvement. Simple probability- and entropy-threshold rules attain comparable interception; conformal's distinct value is a finite-sample fixed-round coverage guarantee together with explicit candidate sets for escalation. Adaptive first-singleton stopping is evaluated empirically and not covered by this guarantee.
Sep 30, 2026

MADBench: Benchmarking the Security of Multi-Agent Debate

Multi-agent debate (MAD) can improve large language model (LLM) reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the interactions that enable agents to correct mistakes can also spread adversarial errors and steer the agents toward an incorrect answer. Although some efforts have been made to examine particular attack types on MAD, systematic evaluation of MAD under diverse attacks remains limited. A central question is whether debate mitigates adversarial influence or amplifies it. In this paper, we present MADBench, a benchmark for evaluating the security of MAD. We organize attacks into a layered taxonomy following the MAD workflow, incorporating both established attacks and new strategies tailored to debate. We evaluate six attack families over 356 source tasks and 3,958 test cases, examining their effects on the final answer and the propagation of adversarial influence. Our results show that, under attacks, MAD does not necessarily improve LLM reasoning. Compared with a single-agent baseline, MAD can mitigate attacks on answer accuracy in question-answering tasks while amplifying unauthorized reads or writes in both question-answering and workspace tasks. Moreover, even when three out of five agents collude, the attack changes the final answer from correct to wrong on only 28.30% of tasks answered correctly without attack, while only 3.26% of initially correct honest agents switch to wrong answers during debate.
Jun 2, 2026

The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation

Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts and viewpoints needed to interpret an issue. We identify the deliberative illusion: discussion produces (1) factual attrition, the progressive loss of issue-critical facts, alongside (2) stance homogenization, the collapse of diverse positions toward consensus. To measure this process, we introduce DelibTrace, a framework that decomposes each issue into atomic facts, labels issue-critical ones, distributes them across agents, and tracks their survival across discussion rounds. Across ethical and news-based deliberation with three representative LLM families, multi-agent discussion erases up to 72% of issue-critical facts. This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context. These results reveal a sharper risk: agents can agree more while knowing less. We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.