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
The quadratic complexity of dense self-attention remains a central bottleneck for long-context language modeling. Many efficient alternatives address this cost by deciding in advance where attention should be sparse or local. We argue that attention approximation should instead be approached as a geometric problem, wit...
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.
