Agentic Conversational Recommender Systems (ACRSs), in which a large language model orchestrates dialogue, item retrieval, and tool use (such as querying item attributes or ranking candidate items), are advancing quickly, yet two problems prevent us from fully understanding their potential and limitations. First, progr...
Alessandro Francesco Maria Martina· Proceedings of the 20th ACM...· 0 citations
This work introduces a stereotype-conditioned, open-weight user simulator that spans three behavioral stereotypes: Direct, Vague-Proactive, and Vague-Reactive, and decomposing the gap into two separable capabilities current ACRSs lack: elicitation and retrieval, which current evaluation entangles in a single score.
Alessandro Petruzzelli, Alessandro Francesco Maria Martina, C. Musto et al.· Proceedings of the 20th ACM...· 1 citation
Agentic Conversational Recommender Systems (ACRSs), in which a large language model orchestrates dialogue, item retrieval, and tool use (such as querying item attributes or ranking candidate items), are advancing quickly, yet two problems prevent us from fully understanding their potential and limitations. First, progr...
Alessandro Francesco Maria Martina· Proceedings of the 20th ACM...· 0 citations
Mixture of Semantic Attention Regimes (MoSAR) is introduced, which learns such an adaptive, controlled-decay geometry over query--key interactions, suggesting that it is not only adaptive, but also amenable to low-cost approximation at inference time.
M. Paolicelli, Alessandro Petruzzelli, Alessandro Francesco Maria Martina et al.· 0 citations
Agentic Conversational Recommender Systems (ACRSs) are designed to recommend through multi-turn dialogue with users whose needs are not fully formed at the outset. However, their evaluation almost exclusively relies on user simulators that instantiate users with clear, pre-formed needs, reducing the interaction to a re...
Alessandro Petruzzelli, Alessandro Francesco Maria Martina, C. Musto et al.· Proceedings of the 20th ACM...· 1 citation
This work introduces a family of open-weight user simulation models capable of generalizing across diverse e-commerce domains and operationalizes three distinct behavioral stereotypes, highlighting the necessity of a scalable framework for rigorously stress-testing the next generation of conversational agents against r...
Alessandro Petruzzelli, Alessandro Francesco Maria Martina, C. Musto et al.· Information Systems Frontier...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
