用自然语言精准表达意图，让推荐系统更懂用户真正想要什么。
Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation
- 构建可执行的意图层，融合显式、隐含、否定和复合意图生成推荐计划。
- 在300个测试请求中精确相关率高达94.4%，优于基线1.11个合格候选。
- 适合关注推荐精度与用户意图对齐的工程团队和产品设计者。
搜索与推荐虽共享发现目标，但意图表达方式不同。本文研究在Threads平台部署的Dear Algo系统，通过开放性请求如“更多NBA新闻”或“减少政治内容”，引导后续推荐流而非返回单一结果列表。其代理式意图层将显式、推断、否定及复合意图整合为可执行计划，并调用传统检索与可选语义或跨模态重排序。该层共享意图到检索的契约，无需统一模型或服务路径即可覆盖搜索与推荐模式。在以精度优先为目标的评估下，300个公开请求-物品对盲审中（296个有效），严格分类的LLM裁判门达到94.4%精确相关率（88.8%, 98.9%）。在72个归一化请求簇中，完整配置每20个槽位产出7.73个裁判合格候选，高于基线6.61，提升1.11（0.12, 2.12）。在仅限重排序路径前72小时的候选随机化服务研究中，用户加权裁判无关占比降至2.80%（基线4.78%），下降1.97点（-3.02, -0.94）；精确相关占比高出2.24点（0.08, 4.41）。整体表明，在精度优先框架下，自然语言意图可有效融入推荐系统。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。