通过表征工程的人格引导识别多智能体情境中的合作型人格
Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering
AI总结：
本研究受重复囚徒困境锦标赛启发，采用表征工程引导 LLM 的大五人格特质，发现宜人性与尽责性可促进合作但更易被剥削。
摘要：
随着大型语言模型（LLM）获得自主能力，它们在多智能体环境中的协调变得日益重要。然而，它们往往难以合作，导致次优结果。受 Axelrod 的重复囚徒困境（IPD）锦标赛启发，我们探讨人格特质如何影响 LLM 的合作。我们利用表征工程，在 LLM 中引导大五人格特质（例如宜人性、尽责性），并分析其对 IPD 决策的影响。结果表明，更高的宜人性和尽责性会提升合作，但也会增加被剥削的易感性，这凸显了基于人格的引导在对齐 AI 智能体方面的潜力与局限。
英文摘要：
As Large Language Models (LLMs) gain autonomous capabilities, their coordination in multi-agent settings becomes increasingly important. However, they often struggle with cooperation, leading to suboptimal outcomes. Inspired by Axelrod's Iterated Prisoner's Dilemma (IPD) tournaments, we explore how personality traits influence LLM cooperation. Using representation engineering, we steer Big Five traits (e.g., Agreeableness, Conscientiousness) in LLMs and analyze their impact on IPD decision-making. Our results show that higher Agreeableness and Conscientiousness improve cooperation but increase susceptibility to exploitation, highlighting both the potential and limitations of personality-based steering for aligning AI agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
