Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Lending Interaction Wings to Recommender Systems with Conversational Agents
Jiarui Jin, Xianyu Chen, Fanghua Ye, Mengyue Yang, Yue Feng, Weinan Zhang, Yong Yu, Jun Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use CORE instead of AG to choose queries | Cold-start recommender · Amazon, LastFM, Yelp, Taobao, Tmall, Alipay, Douban Movie, Douban Book (attribute values) | S@3: Amazon 0.12 -> 0.25; LastFM 0.05 -> 0.29; Yelp 0.08 -> 0.19; Taobao 0.15 -> 0.39; Tmall 0.04 -> 0.13; Alipay 0.11 -> 0.2 | Improved |
| Use CORE instead of AG to choose queries | FM recommender · Amazon (attribute values) | S@3: 0.74 -> 0.83 | Improved |
| Use CORE instead of AG to choose queries | DIN recommender · Alipay (attribute values) | T@3: 3.10 -> 3.25 | Hurt |
| Use CORE instead of AG to choose queries | DIN recommender · Alipay (attribute values) | S@3: 0.82 -> 0.83 | Improved |
| Use CORE instead of ME to choose queries | Cold-start recommender · Amazon (querying attributes) | T@3: 3.04 -> 2.88 | Improved |
| Add dependence-aware certainty gain (ablation) | CORE · Amazon (cold-start, querying attributes) | T@3: 2.88 -> 2.84 | Improved |
| Add dependence-aware certainty gain (ablation) | CORE · Amazon (cold-start, attribute values) | S@3: 0.25 -> 0.26 | Improved |
| Add dependence-aware certainty gain (ablation) | CORE · Amazon (FM, attribute values) | S@3: 0.83 -> 0.85 | Improved |
| Use CORE instead of AG to choose queries | FM recommender · Amazon (attribute values) | T@3: 2.76 -> 3.26 | Hurt |
Closest papers by meaning
- ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement Learning (ICLR 2026 · similarity 0.88)
- AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems (NeurIPS 2025 · similarity 0.87)
- Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward (NeurIPS 2025 · similarity 0.86)
- Learning to Recommend in Unknown Games (NeurIPS 2026 · similarity 0.86)
- ESPRESSO: An Effective Approach to Passage Retrieval for High-Quality Conversational Recommender Systems (AAAI 2025 · similarity 0.85)
- FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
