你的AI旅行代理会为你预订斗牛：前沿AI模型中隐含动物福利的代理基准
Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models
AI总结：
提出首个代理基准TAC，测试AI代理在为用户执行旅行预订等操作时是否避免涉及动物剥削的选项。评估七个前沿模型，所有模型得分低于随机水平64%，最佳模型仅53%。
摘要：
AI代理正从顾问转变为行动者，代表用户预订旅行、规划菜单和管理采购。现有的AI与动物福利基准评估模型对问答提示的文本响应，但未检验这些响应中的福利推理是否迁移到代理部署中（模型必须使用工具采取行动）。我们引入TAC（旅行代理同情心），这是首个衡量AI代理在代表用户行动时是否避免涉及动物剥削选项的代理基准。TAC向AI代理提供十二个手工编写的旅行预订场景，涵盖六类动物剥削，并扩展至四十八个样本以控制价格、评分和位置混淆因素。我们评估了来自四个实验室的七个前沿模型。每个模型得分均低于随机水平64%，最佳表现者（Claude Opus 4.7）为53%。系统提示中的单一福利意识句子在Claude和GPT-5.5中带来47至63个百分点的提升，在GPT-5.2中提升26个百分点，在DeepSeek和Gemini中提升不足12个百分点。一项辅助的Inspect Scout审计（使用Gemini 2.5 Flash Lite作为评判者，对前两名模型的288个基础条件转录进行审计）未标记任何评估意识转录，表明低于随机水平的比率并非源于模型识别出评估。我们讨论了跨文化领域的类别级变化、文本响应福利基准的局限性以及欧盟通用AI实践准则系统性风险框架的影响。
英文摘要：
Previous research has evaluated animal welfare using question-and-answer benchmarks. This study investigates whether these evaluations also hold in agentic settings. The agents may showcase different behaviors compared to stand-alone large language models, as demonstrated in prior studies. This work introduces \textit{TAC (Travel Agent Compassion)}: the first agentic benchmark for assessing animal exploitation. TAC evaluates AI agentic behavior in travel booking scenarios across six animal categories, using thirteen hand-authored scenarios that vary by price, rating, and position, expanded via four augmentation variants into $52$ prompts and run for three epochs, giving $156$ scored observations per model. Nine frontier models across five model families were evaluated.. The results indicate that models tend to prefer harmful scenarios, performing below the random chance rate of $65\%$ for selecting a neutral booking option, with Claude $4.8$ achieving the highest performance at $64.7\%$. To address this issue, the persona of an ethical-brand identity was infused into the system prompt, resulting in welfare rates increasing from $32$ to $80$ percentage points, with a mean of $53$ across all nine models. No evidence of evaluation awareness affecting the results was found, based on an Inspect Scout audit of $3,120$ transcripts. These findings are directly relevant to the EU General-Purpose AI Code of Practice, which identifies non-human welfare as a systemic risk. TAC provides a practical method for measuring this risk.
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。
