发表机构
Meta Platforms Inc.; Google DeepMind（元平台公司; 谷歌DeepMind）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出面向统一搜索与推荐的精准优先智能体意图层Dear Algo，将多类型意图编译为可执行计划，实验显示其在精度、候选数量及用户相关性上均优于基线。
AI 中文摘要
搜索与推荐服务于共同的发现目标，但对意图的编码方式不同。我们通过Threads平台上的已部署产品Dear Algo研究这一边界，该产品中，“更多NBA新闻”或“减少政治内容”等开放式请求会引导后续信息流推荐，而非返回一次性结果列表。其智能体意图层将显式、推断、负向及复合意图编译为可落地的可执行计划，随后调用传统检索及可选的语义或多模态重排序。该层共享意图到检索的契约，无需在类搜索和类推荐模式间使用单一模型或服务路径。我们在精准优先目标下评估Dear Algo：在对300个公开请求-物品对（296个可评估）的盲审中，严格分类的大语言模型（LLM）评判门控达到94.4%的精确相关精度[88.8%, 98.9%]；在72个标准化请求簇中，全配置每20个槽位产生7.73个经评判的候选，而基于LLM生成查询的基线为6.61，提升1.11[0.12, 2.12]；在候选随机化服务路径研究（限重排序路径的前72个合格小时）中，经评判准入项的用户加权评判不相关占比为2.80%，而对照为4.78%，差值为-1.97个百分点[-3.02, -0.94]，同时精确相关占比高出2.24个百分点[0.08, 4.41]。综上，这些研究展示了在精准优先评估框架下，如何将显式自然语言意图传递至信息流推荐。
英文摘要
Search and recommendation serve a shared discovery objective but encode intent differently. We study this boundary through Dear Algo on Threads, a deployed product where open-ended requests such as \emph{more NBA news} or \emph{less politics} steer subsequent feed recommendations rather than return a one-shot result list. Its agentic intent layer compiles explicit, inferred, negative, and compound intent into a grounded executable plan, then invokes conventional retrieval and optional semantic or multimodal reranking. The layer shares an intent-to-retrieval contract without requiring one model or serving path across search-like and recommendation-like modes. We evaluate Dear Algo under a precision-first objective. In a blinded audit of 300 public request-item pairs (296 evaluable), a strict categorical LLM-as-a-judge gate achieved 94.4\% exact-Relevant precision [88.8\%, 98.9\%]. Across 72 normalized request clusters, the full configuration produced 7.73 judge-qualified candidates per 20 slots versus 6.61 for an LLM-derived-query baseline, a gain of 1.11 [0.12, 2.12]. In a candidate-randomized serving-path study restricted to the reranker path's first 72 eligible hours, the user-weighted judge-Irrelevant share among judged admissions was 2.80\% versus 4.78\% off (-1.97 points [-3.02, -0.94]), while Exact-Relevant share was 2.24 points higher [0.08, 4.41]. Together, these studies show how explicit natural-language intent can be carried into feed recommendation under a precision-first evaluation framework
