Searching for Synergy in Shared Workspace Human-AI Collaboration

• URL: http://arxiv.org/abs/2606.18413v3
• Date: Fri, 19 Jun 2026 23:47:07 GMT
• Title: Searching for Synergy in Shared Workspace Human-AI Collaboration
• Abstract summary: We use simulated shared-workspace human-AI teams as a testbed for studying how collaboration structure shapes team behavior.<n>We find that adding additional collaborators can lower performance when coordination structure is absent.<n>We then evaluate collaboration scaffolding that combines shared group memory with simulated human-in-the-loop (HITL) gates.
• Score: 1.4923836729114697
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated AI agents are increasingly capable, yet many scientific and professional tasks require human judgment and contextual expertise. We use simulated shared-workspace human-AI teams as a controlled testbed for studying how collaboration structure shapes team behavior. Using the Collaborative Gym environment with tasks from DiscoveryBench, we vary team compositions and collaboration structures across 1,482 sessions. We find that adding additional collaborators can lower performance when coordination structure is absent. We then evaluate collaboration scaffolding that combines shared group memory with simulated human-in-the-loop (HITL) gates, where selected actions require approval from a designated simulated participant. This scaffolding improves performance, most clearly in three-person teams, with clearer responsibility signals and stronger routing of expertise to team actions. Overall, our results suggest that coordination structure is central to whether available capability improves team outcomes.

Related papers

• 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)
• Beyond Partner Diversity: An Influence-Based Team Steering Framework for Zero-Shot Human-Machine Teaming [1.6672631924542791]
  Influence-Based Team Steering is a framework that uses influence shaping to incentivize agents to discover diverse, high-performing team interaction patterns.<n>We assess IBTS on Overcooked-AI in both two-agent and three-agent settings, allowing us to test whether learned coordination structure transfers beyond dyadic interaction.<n>Our evaluation includes simulated partners, synthetic partner-style variation, and, to our knowledge, the first 30-subject Overcooked-AI HMT study involving two real human teammates and one machine teammate.
  arXiv  Detail & Related papers  (2026-05-14T20:34:16Z)
• CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks [55.84031315625504]
  CollabSkill is a framework for evaluating human-agent collaboration on real-world occupational tasks.<n>It pairs real human workers with AI agents on tasks matched to their occupational background.<n>Our analysis reveals that practical experience emerges as the primary driver of collaboration skill.
  arXiv  Detail & Related papers  (2026-04-20T03:03:25Z)
• TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size [54.0714652192002]
  Physics-based humanoid control has achieved remarkable progress in enabling realistic and high-performing single-agent behaviors.<n>We present TeamHOI, a framework that enables a single decentralized policy to handle cooperative HOIs across any number of cooperating agents.
  arXiv  Detail & Related papers  (2026-03-09T05:52:13Z)
• 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)
• MindAgent: Emergent Gaming Interaction [103.73707345211892]
  Large Language Models (LLMs) have the capacity of performing complex scheduling in a multi-agent system. We propose MindAgent to evaluate planning and coordination emergent capabilities for gaming interaction.
  arXiv  Detail & Related papers  (2023-09-18T17:52:22Z)
• 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)
• Detecting and Optimising Team Interactions in Software Development [58.720142291102135]
  This paper presents a data-driven approach to detect the functional interaction structure for software development teams. Our approach considers differences in the activity levels of team members and uses a block-constrained configuration model. We show how our approach enables teams to compare their functional interaction structure against synthetically created benchmark scenarios.
  arXiv  Detail & Related papers  (2023-02-28T14:53:29Z)

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.