CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement

• URL: http://arxiv.org/abs/2606.05793v1
• Date: Thu, 04 Jun 2026 07:22:44 GMT
• Title: CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
• Abstract summary: CollabBench is a benchmark for evaluating and training collaborative agents in cooperative games.<n>Our trained models achieve 19.5% higher efficiency and 24.4% improved affective performance.
• Score: 28.113758487041995
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views [82.15362247351763]
  We introduce a novel egocentric and exocentric video dataset capturing real-world collaboration in cooking scenarios.<n>The dataset integrates multi-perspective video, high-quality audio, gaze tracking, and 3D scene and object scans, with annotations for shared attention to objects.<n>We establish benchmarks for Joint Attention Estimation, Socially Conditioned Object Interaction Anticipation, and Collaborative Handover Prediction.
  arXiv  Detail & Related papers  (2026-07-07T18:08:45Z)
• CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments [32.043112677406064]
  CollabSim is a simulation framework that combines a theory-grounded definition of collaborative capabilities, controlled manipulation of interaction conditions, and action-level probing of agents' internal states.<n> Experiments show that CollabSim can capture condition effects, separate model performance patterns, and reveal task-dependent effects of agent design.
  arXiv  Detail & Related papers  (2026-06-04T17:06:22Z)
• Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration [54.18136393879849]
  We present ALMANAC, a dataset of action-level mental model ANnotations for Agent Collaboration.<n>ALMANAC contains 2,987 collaboration actions, each paired with theory-informed mental model annotations.<n>Our results demonstrate ALMANAC's utility in evaluating models' ability to simulate human collaborative behaviors.
  arXiv  Detail & Related papers  (2026-06-04T16:56:12Z)
• Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows [26.30514689505384]
  We show that game-derived cooperative profiles robustly predict downstream performance in AI-for-Science tasks.<n>Our framework offers a fast and inexpensive diagnostic for screening cooperative fitness before costly multi-agent deployment.
  arXiv  Detail & Related papers  (2026-04-22T15:07:54Z)
• Learning "Partner-Aware" Collaborators in Multi-Party Collaboration [12.287537011305497]
  Large Language Models (LLMs) are increasingly bring deployed in agentic settings where they act as collaborators with humans.<n>This paper builds on the AI alignment and safe interruptability literature to offer novel theoretical insights on collaborative behavior.<n>We propose Interruptible Collaborative Roleplayer (ICR)-a novel partner-aware learning algorithm to train CG-optimal collaborators.
  arXiv  Detail & Related papers  (2025-10-26T00:05:48Z)
• Improving Cooperation in Collaborative Embodied AI [31.991962631895657]
  The integration of Large Language Models into multiagent systems has opened new possibilities for collaborative reasoning and cooperation with AI agents.<n>This paper explores different prompting methods and evaluates their effectiveness in enhancing agent collaborative behaviour and decision-making.<n>We extend our research by integrating speech capabilities, enabling seamless collaborative voice-based interactions.
  arXiv  Detail & Related papers  (2025-10-03T16:25:48Z)
• Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration [63.90193684394165]
  We introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation.<n>During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards.<n>During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step.
  arXiv  Detail & Related papers  (2025-05-29T07:24:37Z)
• Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models [14.45823275027527]
  Quality Diversity (QD) optimization has been shown to be capable of generating diverse Reinforcement Learning (RL) agent behavior.<n>We first show, through a human-subjects experiment, that humans exhibit diverse coordination and communication behavior in this domain.<n>We then show that our approach can effectively replicate trends from human teaming data and also capture behaviors that are not easily observed.
  arXiv  Detail & Related papers  (2025-04-04T23:09:40Z)
• Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration [50.657070334404835]
  Collaborative Gym is a framework enabling asynchronous, tripartite interaction among agents, humans, and task environments.<n>We instantiate Co-Gym with three representative tasks in both simulated and real-world conditions.<n>Our findings reveal that collaborative agents consistently outperform their fully autonomous counterparts in task performance.
  arXiv  Detail & Related papers  (2024-12-20T09:21:15Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [67.76186488361685]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps.<n>On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• Large Language Model-based Human-Agent Collaboration for Complex Task Solving [94.3914058341565]
  We introduce the problem of Large Language Models (LLMs)-based human-agent collaboration for complex task-solving. We propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process.
  arXiv  Detail & Related papers  (2024-02-20T11:03:36Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.