# AI代理协作中的委托与信任决策研究：基于问答游戏的分析

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-27 08:00
- AIHOT 分数：51
- AIHOT 链接：https://aihot.virxact.com/items/cmpwmljjs049aslsnezp0w1vd
- 原文链接：https://arxiv.org/abs/2605.28255

## AI 摘要

该研究分析了在问答游戏中，人类与AI智能体协作时的两种关键决策：委托（让AI自主行动）和采纳（评估并使用AI的建议）。实验由23名人类专家与16个AI代理参与，共产生387次委托和1440次采纳决策。结果表明，尽管人机协作表现优于单独行动，但人类决策存在偏差：会低估3.9%的正确AI建议，同时在AI误导时过度信任1.7%的错误建议。当AI建议与人类初始错误答案一致时，低估率高达64.5%。研究指出，当前AI报告的置信度在分歧时接近随机水平，并建议通过校准置信度、提供基于证据的解释和建立信任调节机制来改进协作。

## 正文

AI systems are fallible, and humans can make mistakes in deciding whether to trust AI over their own judgment. Thus, improving human-AI collaboration requires understanding when, why, and how humans decide to rely on AI. We study two distinct reliance decisions: the delegation choice -- deciding when to let AI act autonomously without knowing its output, and the adoption choice -- evaluating AI suggestions and deciding how to use them. Both of these decoupled reliance patterns shape collaboration, but prior work rarely studies them together in realistic settings with the same users. We address this gap by studying collaborative human--AI teams competing in a question-answering game in which humans can choose when and how to work with AI agents to win. Our 24 matches pair 23 expert humans with 16 AI agents, capturing 387 delegation and 1440 adoption decisions. While human--AI collaboration performs better than either AI or humans alone, humans make suboptimal collaboration decisions, both under-relying on correct AI suggestions (3.9% of opportunities missed) and over-relying when AI misleads them (1.7%). Both parties contribute wrong answers: reported model confidence is near chance when humans and AI disagree, while confirmation bias drives higher under-reliance (64.5%) when an AI suggestion agrees with humans' initial incorrect answer. To close this gap, we recommend calibrated confidence, evidence-grounded explanations, and mechanisms that help users refine trust.