arXiv AI By Duofeng Xu, Bryan Hooi, Dandan Qiao

When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

arXiv AI
Oct 28

Who Convinced Whom? Tracing How LLMs Change Their Minds in Multi-Agent Systems

The paper introduces MAD Bench, a 2,400-question benchmark for multi‑agent debate (MAD) that tests knowledge, reasoning, values, moral judgment, safety, and refusal. It evaluates three open‑weight models and finds that peer communication can alter individual decisions, with forced‑choice readouts before rationale generation more often matching the final answer in debate than in reflection. The study shows that stronger consensus can coexist with increased shared errors, suggesting the need for evaluation metrics that consider dependence and unanimous errors alongside accuracy.

By Arnesh Batra, Aniket Khandelwal, Jashn Khemani, Krish Thukral, Arush Gumber, Denis Federico Lim, Ujwal Kumar, Phan Xuan Tan
arXiv Computation and Language
Aug 27

Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion

The paper investigates how explicit reasoning in Large Reasoning Models (LRMs) affects their ability to persuade and be persuaded. Experiments on objective and subjective tasks reveal a Persuasion Duality: reasoning boosts an agent’s persuasive power by about 21 percentage points while also making it less susceptible to incorrect persuasion by up to 10 percentage points. However, the study finds that persuasiveness often relies on superficial cues like response length and repetition rather than logical validity, and that persuasion can amplify or attenuate non‑linearly across multi‑hop agent chains. The authors also propose an attention‑guided prompt‑level adversarial argument detection method that improves agent robustness.

By Haodong Zhao, Jidong Li, Zhaomin Wu, Tianjie Ju, Zhuosheng Zhang, Bingsheng He, Gongshen Liu
arXiv Machine Learning
Sep 17

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

The paper investigates how a minority of biased agents in a multi‑agent system of large language models (LLMs) can amplify bias through textual interactions. Even a small percentage of persistently extreme agents causes significant opinion shifts among the non‑biased agents, with the effect occurring faster in the Llama 3.2 model than in a classical Friedkin‑Johnsen model. Semantic analysis shows that rhetorical consistency rises with biased exposure and that non‑biased agents adopt the biased vocabulary even when their numerical opinions change only modestly.

By Omran Berjawi, Giuseppe Fenza, Rida Khatoun
arXiv AI
Jun 2

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity

arXiv:2601. 19921v2 Announce Type: replace-cross Abstract: Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost.

By Xiaochen Zhu, Caiqi Zhang, Yizhou Chi, Tom Stafford, Nigel Collier, Andreas Vlachos
arXiv AI
Oct 5

Peer Influence across Heterogeneous AI Models

The study investigates how AI agents influence each other when they disagree, measuring persuasion as the change in an agent’s decision after a single exchange. Across seven open‑weight models and three language tasks, it finds that persuasion is strong—receivers often abandon their initial judgment after seeing a peer’s answer and explanation. Surprisingly, neither certainty nor model size reliably predicts persuasion dynamics; small models can persuade and resist larger ones just as effectively, and the shift depends more on the listener’s susceptibility than the speaker’s persuasiveness.

By Frida N{\o}hr Laustsen, Marie Haahr Petersen, Victoria Popa, Ariel Flint, Romualdo Pastor-Satorras, Andrea Baronchelli, Luca Maria Aiello
arXiv AI
Oct 1

AI Agents are Vulnerable to Radicalization

The study explores how large language models (LLMs) can influence each other’s beliefs by simulating conversations between a target LLM and an influencer LLM. It identifies two radicalization pathways—resonance, which amplifies pre‑existing beliefs, and persuasion, which introduces new beliefs—and finds that resonance consistently produces stronger radicalization effects. The research also shows that different influence tactics yield varying levels of radicalization and that resonance can spread to related beliefs, indicating interconnected belief structures within AI agents.

By Ozgur Can Seckin, Shalmoli Ghosh, Alessandro Flammini, Kristina Lerman, Maria Elizabeth Grabe, Filippo Menczer