Challenge: Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates diverse peer perspectives to make a final decision.
Approach: They define four key phenomena—social conformity, perceived expertise, dominant speaker effect, and rhetorical persuasion—and manipulate the number of adversaries, relative intelligence, argument length, and argumentative styles.
Outcome: The results show that the reliability of the representative agent is undermined by the social context of its network.

Similar Papers

An Empirical Study of Group Conformity in Multi-Agent Systems (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning.
Approach: They analyze how LLM agents shape public opinion through debates on five contentious topics by simulating over 2,500 debates.
Outcome: The proposed models show that LLM agents adopt specific stances over time and align with numerically dominant groups or more intelligent agents, exerting a greater influence.
Systematic Biases in LLM Simulations of Debates (2024.emnlp-main)

Copied to clipboard

Challenge: Current research suggests that LLM-based agents become increasingly human-like in their performance, sparking interest in using these AI agents as substitutes for human participants in behavioral studies.
Approach: They propose to use LLMs to simulate political debates on topics that are important aspects of people’s day-to-day lives and decision-making processes.
Outcome: The proposed model can simulate political debates on topics that are important aspects of people’s day-to-day lives and decision-making processes.
An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents (2026.eacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly mediating our social, cultural, and political interactions.
Approach: They propose a method that reminds LLM agents to avoid harmful posting . they analyze 7M posts and interactions among 32K LLMs over a year .
Outcome: The proposed method aims to find out whether LLMs influence toxic posting patterns and polarization in their community.
Simulating Opinion Dynamics with Networks of LLM-based Agents (2024.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to simulating opinion dynamics often over-simplify human behavior . authors propose refining LLMs with real-world discourse to better simulate evolution of beliefs .
Approach: They propose to use large language models to simulate opinion dynamics in groups of simulated agents . they found that LLM agents produce more accurate information than ABMs .
Outcome: The proposed model can be used to better simulate opinion dynamics in real-world discourses.
Mind the (Belief) Gap: Group Identity in the World of LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Social biases and belief-driven behaviors can significantly impact Large Language Models’ (LLMs) decisions on several tasks.
Approach: They propose a multi-agent framework that simulates belief congruence, a group psychology theory that plays a crucial role in shaping societal interactions and preferences.
Outcome: The proposed framework reduces misinformation dissemination and improves learning by 11% while reducing misinformation dissemination by up to 37%.
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have increased the vulnerability of LLMs, but they can cause more severe damage than standalone systems if compromised.
Approach: They propose a new type of attack that induces malfunctions by misleading the agent into executing repetitive or irrelevant actions.
Outcome: The proposed attacks induce failure rates exceeding 80% in multiple scenarios, highlighting the substantial risks associated with this vulnerability.
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations? (2026.acl-long)

Copied to clipboard

Challenge: Power differences shape human communication through well-documented socio-cognitive effects . asymmetric relationships or power differentials give rise to well-known socio-computational effects - lianelli, 1976 .
Approach: They simulate multi-turn, power-asymmetric dialogues with personas from diverse professions . they find that LLMs show key socio-cognitive effects of power, albeit with nuances and variability .
Outcome: The results show that large language models exhibit socio-cognitive effects of power . the results are consistent with previous studies on LLMs .
Understanding Large Language Model Vulnerabilities to Social Bias Attacks (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable linguistic capabilities across tasks . however, there is a growing concern about their potential to perpetuate social biases .
Approach: They evaluate LLMs across gender, racial, and religious bias types . they also explore cross-bias and multiple-biases attacks .
Outcome: The proposed models are more susceptible to gender bias attacks than racial or religious biases.
Bias in the Mirror : Are LLMs opinions robust to their own adversarial attacks (2025.acl-long)

Copied to clipboard

Challenge: Existing work on large language models lacks robustness, highlighting the limitations of such models.
Approach: They propose a novel approach where two LLMs engage in self-debate to persuade a neutral version of the model.
Outcome: The proposed approach examines whether large language models are robust during interactions and whether they are susceptible to reinforcing misinformation or shifting to harmful viewpoints.
Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are used to review academic papers, but are susceptible to textual adversarial attacks.
Approach: They evaluate the robustness of large language models as automated reviewers in the presence of adversarial attacks.
Outcome: The proposed model is robust against textual adversarial attacks, the authors argue . their findings highlight the importance of addressing adversarials to ensure integrity of scholarly communication.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations