arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.06151cs.LGcs.AIcs.HC
收藏

LLMs作为策略无关的队友:异构智能体团队中人类代理设计的案例研究

LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams

School of Computer Science, University of Birmingham(伯明翰大学计算机科学学院)

Aju Ani Justus, Chris Baber

AI总结:

本研究提出用LLMs作为策略无关的人类代理生成合成数据,以解决异构智能体团队训练中人类数据昂贵的问题,实验表明LLMs输出与专家决策对齐且能模拟人类风险行为变异性,为策略无关队友模拟提供可扩展基础。

摘要:

建模异构智能体团队的一个关键挑战是训练智能体与策略不可访问或非平稳的队友(如人类)协作。传统方法依赖昂贵的人机交互数据,这限制了可扩展性。我们提出使用大型语言模型(LLMs)作为策略无关的人类代理,生成模拟人类决策的合成数据。为评估这一方法,我们在受“猎鹿博弈”启发的网格世界捕获游戏中进行了三项实验,该博弈论范式平衡了风险与回报。实验1中,我们将30名人类参与者和2名专家评审的决策与LLaMA 3.1和Mixtral 8x22B模型的输出进行比较。使用游戏状态观察和奖励结构提示的LLMs与专家的对齐程度高于参与者,展示了应用底层决策标准的一致性。实验2修改提示以诱导风险敏感策略(例如“风险规避”)。LLM输出反映了人类参与者的变异性,在风险规避和风险寻求行为之间切换。最后,实验3在动态网格世界中测试LLMs,其中LLM智能体生成移动动作。LLMs产生的轨迹类似于人类参与者的路径。虽然LLMs尚不能完全复制人类的适应性,但其提示引导的多样性为模拟策略无关队友提供了可扩展的基础。

英文摘要:

A critical challenge in modelling Heterogeneous-Agent Teams is training agents to collaborate with teammates whose policies are inaccessible or non-stationary, such as humans. Traditional approaches rely on expensive human-in-the-loop data, which limits scalability. We propose using Large Language Models (LLMs) as policy-agnostic human proxies to generate synthetic data that mimics human decision-making. To evaluate this, we conduct three experiments in a grid-world capture game inspired by Stag Hunt, a game theory paradigm that balances risk and reward. In Experiment 1, we compare decisions from 30 human participants and 2 expert judges with outputs from LLaMA 3.1 and Mixtral 8x22B models. LLMs, prompted with game-state observations and reward structures, align more closely with experts than participants, demonstrating consistency in applying underlying decision criteria. Experiment 2 modifies prompts to induce risk-sensitive strategies (e.g. "be risk averse"). LLM outputs mirror human participants' variability, shifting between risk-averse and risk-seeking behaviours. Finally, Experiment 3 tests LLMs in a dynamic grid-world where the LLM agents generate movement actions. LLMs produce trajectories resembling human participants' paths. While LLMs cannot yet fully replicate human adaptability, their prompt-guided diversity offers a scalable foundation for simulating policy-agnostic teammates.

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。

↑