{"type":"ScholarlyArticle","title":"LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection","authors":[{"name":"Adam S. Jovine","slug":"adam-s-jovine","given":"Adam S.","family":"Jovine","affiliation":""},{"name":"Tinghan Ye","slug":"tinghan-ye","given":"Tinghan","family":"Ye","affiliation":""},{"name":"Francis Bahk","slug":"francis-bahk","given":"Francis","family":"Bahk","affiliation":""},{"name":"Jingjing Wang","slug":"jingjing-wang","given":"Jingjing","family":"Wang","affiliation":""},{"name":"Matthew Ford","slug":"matthew-ford","given":"Matthew","family":"Ford","affiliation":""},{"name":"David B. Shmoys","slug":"david-b-shmoys","given":"David B.","family":"Shmoys","affiliation":""},{"name":"Peter I. Frazier","slug":"peter-i-frazier","given":"Peter I.","family":"Frazier","affiliation":""}],"abstract":"Human experts often struggle to select the best option from a large set of items with multiple competing objectives, a process bottlenecked by the difficulty of formalizing complex, implicit preferences. To address this, we introduce LISTEN (LLM-based Iterative Selection with Trade-off Evaluation from Natural-language), an agentic LLM-based framework that treats the LLM as a decision-making agent capable of iteratively refining its internal preference model and taking actions (e.g., proposing utilities or selecting candidates) to maximize alignment with a user's implicit goals. To operate within LLM constraints like context windows and inference costs, we propose two iterative algorithms: LISTEN-U, which uses the LLM to refine a parametric utility function, and LISTEN-T, a non-parametric method that performs tournament-style selections over small batches of solutions. Evaluated on diverse tasks including flight booking, shopping, and exam scheduling, our results show LISTEN-U excels when preferences are parametrically aligned (a property we measure with a novel concordance metric), while LISTEN-T offers more robust performance overall. This work explores a promising direction for steering complex multi-objective decisions directly with natural language, reducing the cognitive burden of traditional preference elicitation. Code is available at https://github.com/AdamJovine/LISTEN.","doi":"10.24963/ijcai.2026/403","url":"https://ijcai.org/proceedings/2026/403","pdf":"https://ijcai.org/proceedings/2026/0403.pdf","markdown":"https://ijcai.org/proceedings/2026/403.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/403","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Humans and AI","track":"Main Track","number":403,"pages":{"first":3621,"last":3629},"keywords":["Natural Language Processing: Language models","Humans and AI: Personalization and user modeling","Knowledge Representation and Reasoning: Preference modelling and preference-based reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}