aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分54

卡内基梅隆大学研究:展示具体选项有助于规划代理找到用户愿意接受的方案

AI 导读

一则介绍卡内基梅隆大学论文的帖子称,规划旅行或购物时,用户可能在看到具体选项后接受超出原先条件的取舍。帖子举例说,将一项未说出的取舍加入需求后,同一规划器生成的方案中,用户接受比例从12%升至55%;这一结果仍需结合论文的实验条件核对。

原帖引用 · AI 翻译

@rohanpaul_ai
译文 · 以原文为准

– https://t.co/fNh4JUOMue

标题:“规划智能体应如何重塑其搜索空间?”

回复Rohan Paul@rohanpaul_ai
译文
卡内基梅隆大学的一篇新论文发现,规划旅行和购物的 AI 助手,与其询问人们的偏好,不如向他们展示几个真实选项,这样能找到更多人们愿意接受的选择。 像“评分在 3.8 或以上的餐厅”这样的旅行需求,会排除一家评分为 3.7、价格更低,而用户其实很愿意选的餐厅。人们很少会主动说自己愿意为了省钱接受较低的评分,因为只有看到实际选项时,他们才会意识到这一点。 > 在使用同一个规划器的情况下,将这 1 个未明说的取舍加入需求后,用户接受的方案比例从 12% 提高到 55%。 > 当前的智能体(Claude Code、Gemini CLI 等)大多只是提问,很少展示方案,因此最多只能发现用户愿意接受的方案中的 32%。 > 展示方案的智能体明显比提问的智能体表现更好。 当你的智能体把需求转化为方案时,应在确定需求细则之前,尽早向用户展示几个超出其明示限制的选项。
原文

New Carnegie Mellon paper finds that AI assistants that plan trips and shopping find more options people would accept by showing them a few real choices than by asking about their preferences. A travel request like “restaurants rated 3.8 or higher” throws out a cheaper place rated 3.7 that the user would happily pick. People rarely say they would accept a lower rating to save money, because they only realize it when they see the actual options. > Adding that 1 hidden trade-off to the request raised the share of plans the user accepted from 12% to 55%, with the same planner. > Current agents (Claude Code, Gemini CLI and others) mostly asked questions and rarely showed plans, so they caught at most 32% of plans the user would accept. > Agents that showed plans did clearly better than agents that asked. When your agent turns a request into a plan, show the user a few options outside their stated limits early, before locking the spec.

在 X 查看这条帖子 ↗

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错