{"ID":3083849,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T06:54:00.442624098Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05793","arxiv_id":"2606.05793","title":"CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement","abstract":"While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative studies lack grounded interaction and behavioral execution, motivating the need for cooperative game environments that enable contextualized and immersive collaboration. To this end, this paper proposes CollabBench, a benchmark for evaluating and training collaborative agents in cooperative games. CollabBench features a Diverse Player Profile Simulation pipeline to model varied players behaviors, and a Collaborative Agentic Training paradigm that unifies reasoning, communication, and action via agentic rollouts, optimized with a hybrid reward balancing task efficiency and affective adaptation. We further extend classic environments to CWAH-MultiPlayer and Cook-MultiPlayer for systematic evaluation under diverse personalities. Experiments with efficiency and affective metrics show that our trained models outperform base models, achieving 19.5% higher efficiency and 24.4% improved affective performance. Further analysis reveals key collaborative limitations of existing models and offers insights for future collaborative training.","short_abstract":"While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative studies lack grounded interaction and behavioral execution, motivating the need for cooperative game environments that enable contextualized...","url_abs":"https://arxiv.org/abs/2606.05793","url_pdf":"https://arxiv.org/pdf/2606.05793v1","authors":"[\"Hong Qian\",\"Yuanhao Liu\",\"Zihan Zhou\",\"Zongbao Zhang\",\"Hanjie Ge\",\"Haotian Shi\",\"Liang Dou\",\"Xiangfeng Wang\",\"Jingwen Yang\",\"Aimin Zhou\"]","published":"2026-06-04T07:22:44Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.CY\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}