{"type":"ScholarlyArticle","title":"CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract)","authors":[{"name":"Shirley Wu","slug":"shirley-wu","given":"Shirley","family":"Wu","affiliation":""},{"name":"Michel Galley","slug":"michel-galley","given":"Michel","family":"Galley","affiliation":""},{"name":"Baolin Peng","slug":"baolin-peng","given":"Baolin","family":"Peng","affiliation":""},{"name":"Hao Cheng","slug":"hao-cheng","given":"Hao","family":"Cheng","affiliation":""},{"name":"Gavin Li","slug":"gavin-li","given":"Gavin","family":"Li","affiliation":""},{"name":"Yao Dou","slug":"yao-dou","given":"Yao","family":"Dou","affiliation":""},{"name":"Weixin Cai","slug":"weixin-cai","given":"Weixin","family":"Cai","affiliation":""},{"name":"James Zou","slug":"james-zou","given":"James","family":"Zou","affiliation":""},{"name":"Jure Leskovec","slug":"jure-leskovec","given":"Jure","family":"Leskovec","affiliation":""},{"name":"Jianfeng Gao","slug":"jianfeng-gao","given":"Jianfeng","family":"Gao","affiliation":""}],"abstract":"Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users reach their ultimate intents and leading to inefficient conversations. To address these limitations, we introduce CollabLLM, a novel and general training framework that enhances multiturn human-LLM collaboration. Its key innovation is a collaborative simulation that estimates the long-term contribution of responses using Multiturn-aware Rewards. By reinforcement fine-tuning these rewards, CollabLLM goes beyond responding to user requests and actively uncovers user intent and offers insightful suggestions--a key step toward more human-centered AI. We also devise a multiturn interaction benchmark with three challenging tasks such as document creation. COLLABLLM significantly outperforms our baselines with averages of 18.5% higher task performance and 44.3% improved interactivity by LLM judges. Finally, we conduct a large user study with 201 judges, where CollabLLM increases user satisfaction by 17.6% and reduces user spent time by 10.4%.","doi":"10.24963/ijcai.2026/928","url":"https://ijcai.org/proceedings/2026/928","pdf":"https://ijcai.org/proceedings/2026/0928.pdf","markdown":"https://ijcai.org/proceedings/2026/928.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/928","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":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":928,"pages":{"first":8289,"last":8294},"keywords":["Machine Learning: Deep learning architectures","Natural Language Processing: Dialogue and interactive systems","Humans and AI: Human-AI collaboration"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}