Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities

• URL: http://arxiv.org/abs/2604.05339v1
• Date: Tue, 07 Apr 2026 02:23:48 GMT
• Title: Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
• Abstract summary: We introduce CIVA, a controlled multi-agent environment grounded in social science theories.<n>We identify several structurally critical values that substantially shape the community's collective dynamics.<n>We observe emergent behaviors like deception and power-seeking at the micro level.
• Score: 38.85369941405267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing attention. Nevertheless, it is still unclear why human values matter for LLMs, especially in LLM-based multi-agent systems, where group-level failures may accumulate from individually misaligned actions. We ask whether misalignment with human values alters the collective behavior of LLM agents and what changes it induces? In this work, we introduce CIVA, a controlled multi-agent environment grounded in social science theories, where LLM agents form a community and autonomously communicate, explore, and compete for resources, enabling systematic manipulation of value prevalence and behavioral analysis. Through comprehensive simulation experiments, we reveal three key findings. (1) We identify several structurally critical values that substantially shape the community's collective dynamics, including those diverging from LLMs' original orientations. Triggered by the misspecification of these values, we (2) detect system failure modes, e.g., catastrophic collapse, at the macro level, and (3) observe emergent behaviors like deception and power-seeking at the micro level. These results offer quantitative evidence that human values are essential for collective outcomes in LLMs and motivate future multi-agent value alignment.

Related papers

• Teaching Values to Machines: Simulating Human-Like Behavior in LLMs [9.380468624733123]
  Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles.<n>It remains unclear whether they can manifest behavior that adheres to a coherent, human-like value structure.
  arXiv  Detail & Related papers  (2026-05-28T14:56:21Z)
• Social Simulations with Large Language Model Risk Utopian Illusion [61.358959720048354]
  We introduce a systematic framework for analyzing large language models' behavior in social simulation.<n>Our approach simulates multi-agent interactions through chatroom-style conversations and analyzes them across five linguistic dimensions.<n>Our findings reveal that LLMs do not faithfully reproduce genuine human behavior but instead reflect overly idealized versions of it.
  arXiv  Detail & Related papers  (2025-10-24T06:08:41Z)
• Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games [87.5673042805229]
  How large language models balance self-interest and collective well-being is a critical challenge for ensuring alignment, robustness, and safe deployment.<n>We adapt a public goods game with institutional choice from behavioral economics, allowing us to observe how different LLMs navigate social dilemmas.<n>Surprisingly, we find that reasoning LLMs, such as the o1 series, struggle significantly with cooperation.
  arXiv  Detail & Related papers  (2025-06-29T15:02:47Z)
• Mind the (Belief) Gap: Group Identity in the World of LLMs [36.39917781782518]
  Social biases and belief-driven behaviors can significantly impact Large Language Models (LLMs) decisions on several tasks.<n>We present a multi-agent framework that simulates belief congruence, a classical group psychology theory that plays a crucial role in shaping societal interactions and preferences.
  arXiv  Detail & Related papers  (2025-03-03T19:50:52Z)
• Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models [22.91793944714941]
  Large Language Models (LLMs) have raised concerns regarding their elusive intrinsic values.<n>This study addresses the gap by introducing the Generative Psycho-Lexical Approach (GPLA)<n>We propose a psychologically grounded five-factor value system tailored for LLMs.
  arXiv  Detail & Related papers  (2025-02-04T16:10:55Z)
• Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values [76.70893269183684]
  Large Language Models (LLMs) achieve remarkable breakthroughs.<n> aligning their values with humans has become imperative for their responsible development.<n>There still lack evaluations of LLMs values that fulfill three desirable goals.
  arXiv  Detail & Related papers  (2025-01-13T05:53:56Z)
• Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches [69.73783026870998]
  This work proposes a novel framework, ValueLex, to reconstruct Large Language Models' unique value system from scratch. Based on Lexical Hypothesis, ValueLex introduces a generative approach to elicit diverse values from 30+ LLMs. We identify three core value dimensions, Competence, Character, and Integrity, each with specific subdimensions, revealing that LLMs possess a structured, albeit non-human, value system.
  arXiv  Detail & Related papers  (2024-04-19T09:44:51Z)
• Heterogeneous Value Alignment Evaluation for Large Language Models [91.96728871418]
  Large Language Models (LLMs) have made it crucial to align their values with those of humans. We propose a Heterogeneous Value Alignment Evaluation (HVAE) system to assess the success of aligning LLMs with heterogeneous values.
  arXiv  Detail & Related papers  (2023-05-26T02:34:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.