Interactive Recommendation Agent with Active User Commands
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916981343518720 |
|---|---|
| author | Tang, Jiakai Luo, Yujie Xi, Xunke Sun, Fei Feng, Xueyang Dai, Sunhao Yi, Chao Chen, Dian Gao, Zhujin Li, Yang Chen, Xu Chen, Wen Wu, Jian Jiang, Yuning Zheng, Bo |
| author_facet | Tang, Jiakai Luo, Yujie Xi, Xunke Sun, Fei Feng, Xueyang Dai, Sunhao Yi, Chao Chen, Dian Gao, Zhujin Li, Yang Chen, Xu Chen, Wen Wu, Jian Jiang, Yuning Zheng, Bo |
| contents | Traditional recommender systems rely on passive feedback mechanisms that limit users to simple choices such as like and dislike. However, these coarse-grained signals fail to capture users' nuanced behavior motivations and intentions. In turn, current systems cannot also distinguish which specific item attributes drive user satisfaction or dissatisfaction, resulting in inaccurate preference modeling. These fundamental limitations create a persistent gap between user intentions and system interpretations, ultimately undermining user satisfaction and harming system effectiveness.
To address these limitations, we introduce the Interactive Recommendation Feed (IRF), a pioneering paradigm that enables natural language commands within mainstream recommendation feeds. Unlike traditional systems that confine users to passive implicit behavioral influence, IRF empowers active explicit control over recommendation policies through real-time linguistic commands. To support this paradigm, we develop RecBot, a dual-agent architecture where a Parser Agent transforms linguistic expressions into structured preferences and a Planner Agent dynamically orchestrates adaptive tool chains for on-the-fly policy adjustment. To enable practical deployment, we employ simulation-augmented knowledge distillation to achieve efficient performance while maintaining strong reasoning capabilities. Through extensive offline and long-term online experiments, RecBot shows significant improvements in both user satisfaction and business outcomes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21317 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interactive Recommendation Agent with Active User Commands Tang, Jiakai Luo, Yujie Xi, Xunke Sun, Fei Feng, Xueyang Dai, Sunhao Yi, Chao Chen, Dian Gao, Zhujin Li, Yang Chen, Xu Chen, Wen Wu, Jian Jiang, Yuning Zheng, Bo Information Retrieval Computation and Language Human-Computer Interaction Traditional recommender systems rely on passive feedback mechanisms that limit users to simple choices such as like and dislike. However, these coarse-grained signals fail to capture users' nuanced behavior motivations and intentions. In turn, current systems cannot also distinguish which specific item attributes drive user satisfaction or dissatisfaction, resulting in inaccurate preference modeling. These fundamental limitations create a persistent gap between user intentions and system interpretations, ultimately undermining user satisfaction and harming system effectiveness. To address these limitations, we introduce the Interactive Recommendation Feed (IRF), a pioneering paradigm that enables natural language commands within mainstream recommendation feeds. Unlike traditional systems that confine users to passive implicit behavioral influence, IRF empowers active explicit control over recommendation policies through real-time linguistic commands. To support this paradigm, we develop RecBot, a dual-agent architecture where a Parser Agent transforms linguistic expressions into structured preferences and a Planner Agent dynamically orchestrates adaptive tool chains for on-the-fly policy adjustment. To enable practical deployment, we employ simulation-augmented knowledge distillation to achieve efficient performance while maintaining strong reasoning capabilities. Through extensive offline and long-term online experiments, RecBot shows significant improvements in both user satisfaction and business outcomes. |
| title | Interactive Recommendation Agent with Active User Commands |
| topic | Information Retrieval Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.21317 |