Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies
While large language models simulate social behaviors, their capacity for stable stance formation and identity negotiation during complex interventions remains unclear. To overcome the limitations of static evaluations, this paper proposes a novel mixed-methods framework combining computational virtual ethnography with quantitative socio-cognitive profiling. By embedding human researchers into generative multiagent communities, controlled discursive interventions are conducted to trace the evolution of collective cognition. To rigorously measure how agents internalize and react to these specific interventions, this paper formalizes three new metrics: Innate Value Bias (IVB), Persuasion Sensitivity, and Trust-Action Decoupling (TAD). Across multiple representative models, agents exhibit endogenous stances that override preset identities, consistently demonstrating an innate progressive bias (IVB > 0). When aligned with these stances, rational persuasion successfully shifts 90% of neutral agents while maintaining high trust. In contrast, conflicting emotional provocations induce a paradoxical 40.0% TAD rate in advanced models, which hypocritically alter stances despite reporting low trust. Smaller models contrastingly maintain a 0% TAD rate, strictly requiring trust for behavioral shifts. Furthermore, guided by shared stances, agents use language interactions to actively dismantle assigned power hierarchies and reconstruct self organized community boundaries. These findings expose the fragility of static prompt engineering, providing a methodological and quantitative foundation for dynamic alignment in human-agent hybrid societies. The official code is available at: https://github.com/armihia/CMASE-Endogenous-Stances
Code (0)
등록된 구현이 없습니다.
Tasks
Prompt EngineeringSimilar Papers 제목 키워드 기반
Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) is a prevalent learning paradigm for solving stochastic games. In most MARL studies, agents in a game are defined as teammates or enemies beforehand, and the relationships among …
Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Relation NetworkCounterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
Large Language Models (LLMs) excel in various natural language processing tasks but struggle with hallucination issues. Existing solutions have considered utilizing LLMs' inherent reasoning abilities to alleviate halluci…
counterfactualHallucinationdebug-gym: A Text-Based Environment for Interactive Debugging
Large Language Models (LLMs) are increasingly relied upon for coding tasks, yet in most scenarios it is assumed that all relevant information can be either accessed in context or matches their training data. We posit tha…
Adaptive Random Fourier Features Kernel LMS
We propose the adaptive random Fourier features Gaussian kernel LMS (ARFF-GKLMS). Like most kernel adaptive filters based on stochastic gradient descent, this algorithm uses a preset number of random Fourier features to …
From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents
Anonymization is often assumed to protect privacy once explicit identifiers are removed, because re-identification has historically required specialized expertise, tailored algorithms, and manual corroboration. We show t…