CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract)

Wu, Shirley; Galley, Michel; Peng, Baolin; Cheng, Hao; Li, Gavin; Dou, Yao; Cai, Weixin; Zou, James; Leskovec, Jure; Gao, Jianfeng

doi:10.24963/ijcai.2026/928

CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract)

Shirley Wu, Michel Galley, Baolin Peng, Hao Cheng, Gavin Li, Yao Dou, Weixin Cai, James Zou, Jure Leskovec, Jianfeng Gao

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Sister Conferences Best Papers. Pages 8289-8294.

https://doi.org/10.24963/ijcai.2026/928

Keywords

Machine Learning: Deep learning architectures
Natural Language Processing: Dialogue and interactive systems
Humans and AI: Human-AI collaboration

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%.

Shirley Wu, Michel Galley, Baolin Peng, Hao Cheng, Gavin Li, Yao Dou, Weixin Cai, James Zou, Jure Leskovec, and Jianfeng Gao. 2026. CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract). In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8289–8294. https://doi.org/10.24963/ijcai.2026/928

@inproceedings{ijcai2026p928,
  title     = {CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract)},
  author    = {Wu, Shirley and Galley, Michel and Peng, Baolin and Cheng, Hao and Li, Gavin and Dou, Yao and Cai, Weixin and Zou, James and Leskovec, Jure and Gao, Jianfeng},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8289--8294},
  year      = {2026},
  month     = {8},
  note      = {Sister Conferences Best Papers},
  doi       = {10.24963/ijcai.2026/928},
  url       = {https://doi.org/10.24963/ijcai.2026/928},
}

TY  - CPAPER
TI  - CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract)
AU  - Wu, Shirley
AU  - Galley, Michel
AU  - Peng, Baolin
AU  - Cheng, Hao
AU  - Li, Gavin
AU  - Dou, Yao
AU  - Cai, Weixin
AU  - Zou, James
AU  - Leskovec, Jure
AU  - Gao, Jianfeng
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8289
EP  - 8294
DO  - 10.24963/ijcai.2026/928
UR  - https://doi.org/10.24963/ijcai.2026/928
ER  -