发表机构
Harvard University; MIT（哈佛大学; 麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过拍卖和匹配实验，发现简单接口和文本脚手架能改善LLM智能体决策，但行为改进与解释质量提升并不总是同步。
AI 中文摘要
交互格式和文本脚手架能否帮助大型语言模型（LLM）智能体做出更好的决策，并且更好的决策是否伴随着更好的解释？我们在拍卖和匹配这两种具有明确规则和已知最优策略的多智能体环境中研究这些问题。这些设置使我们能够在保留评估行为基准的同时，改变决策问题的呈现方式。借鉴以人类动机为基础的简洁性理论，我们比较了引出完整出价或排名的接口与使安全选择更易于识别的顺序接口。然后，我们固定交互格式，改变推理脚手架和规则描述。在四个模型家族中，升序拍卖接口显著减少了出价偏差。匹配比较也表明，为什么顺序响应需要与完整排名不同的错误核算。列出收益条件并解释为什么说真话是安全的也能改善选择，而提示规划匹配轮次或形成对对手的信念则总体上使表现变差。在拍卖中，这些行为上的改进并未伴随智能体简短陈述计划中战略理解的可测量言语指标的相应改善。其他提示改变了这些指标，却没有改善出价。我们的发现表明，以人类动机为基础的简洁性理论可以为人工智能体的决策环境设计提供信息。它们还说明了为什么脚手架应通过实际选择以及解释来评估：一方面的改进不一定出现在另一方面。
英文摘要
Can interaction formats and textual scaffolds help large language model (LLM) agents make better decisions, and do better decisions come with better explanations? We study these questions in auctions and matching, multi-agent environments with explicit rules and known optimal strategies. These settings let us vary how a decision problem is presented while retaining a benchmark for evaluating behavior. Drawing on human-motivated theories of simplicity, we compare interfaces that elicit a complete bid or ranking with sequential interfaces that make safe choices easier to identify. We then hold the interaction format fixed and vary reasoning scaffolds and rule descriptions. Across four model families, the ascending auction interface substantially reduces bid deviations. The matching comparison also shows why sequential responses require different error accounting from complete rankings. Laying out payoff contingencies and explaining why truth-telling is safe also improve choices, whereas prompts to plan through matching rounds or form beliefs about opponents worsen play overall. In auctions, these behavioral gains are not accompanied by corresponding improvements in measured verbal indicators of strategic understanding in the agents' short stated plans. Other prompts change those indicators without improving bids. Our findings suggest that human-motivated theories of simplicity can inform the design of decision environments for artificial agents. They also show why scaffolds should be evaluated through realized choices as well as explanations: improvements in one need not appear in the other.
