Paper Number
ICIS2026-1958
Paper Type
Completed
Abstract
Conversational recommender systems (CRSs) struggle with vague user intent: existing LLM-based approaches rely on reactive questioning, underutilize experience from historical dialogues, and lack decision-theoretic sequential optimization. Adopting a design science paradigm, we develop the Socratic Collaborative Conversational Recommender System (SCCRS), a multi-agent artifact that reconceptualizes recommendation as preference co-construction under partial observability. SCCRS integrates (1) Socratic preference elicitation that actively scaffolds user sensemaking to clarify vague user intents, (2) collaborative experience retrieval that transforms historical trajectories into pseudo-gradient signals guiding dialogue planning, and (3) a POMDP formalization balancing exploration and exploitation. LLM-simulated evaluations on REDIAL and OpenDialKG show that SCCRS significantly outperforms state-of-the-art baselines in recommendation success, dialogue efficiency, and ranking accuracy. This study contributes a systematically evaluated artifact and design principles for adaptive, experience-driven conversational decision support.
Recommended Citation
Zhang, Haoran; Li, Wenhua; and Guo, Junpeng, "Towards Collaborative Conversational Recommendation: A Multi-Agent Framework with Socratic Intent Elicitation and Experience Retrieval" (2026). ICIS 2026 Proceedings. 3.
https://aisel.aisnet.org/icis2026/computational/computational/3
Towards Collaborative Conversational Recommendation: A Multi-Agent Framework with Socratic Intent Elicitation and Experience Retrieval
Conversational recommender systems (CRSs) struggle with vague user intent: existing LLM-based approaches rely on reactive questioning, underutilize experience from historical dialogues, and lack decision-theoretic sequential optimization. Adopting a design science paradigm, we develop the Socratic Collaborative Conversational Recommender System (SCCRS), a multi-agent artifact that reconceptualizes recommendation as preference co-construction under partial observability. SCCRS integrates (1) Socratic preference elicitation that actively scaffolds user sensemaking to clarify vague user intents, (2) collaborative experience retrieval that transforms historical trajectories into pseudo-gradient signals guiding dialogue planning, and (3) a POMDP formalization balancing exploration and exploitation. LLM-simulated evaluations on REDIAL and OpenDialKG show that SCCRS significantly outperforms state-of-the-art baselines in recommendation success, dialogue efficiency, and ranking accuracy. This study contributes a systematically evaluated artifact and design principles for adaptive, experience-driven conversational decision support.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
10_Computational_design