Topics include, but are not limited to:

The workshop welcomes original theoretical, methodological, empirical, and design-oriented contributions on multi-agent and agentic systems in organizational settings. Interdisciplinary contributions are welcome.
Topics include, but are not limited to:

Agent Architectures and Orchestration

• Centralized, decentralized, and hybrid architectures
• Orchestration of agents across organizational processes
• Agent composition, workflow management, task decomposition, and delegation
• Agent role, specialization, lifecycle, state, and resource management

Interoperability and Enterprise Integration of Agents

• Agent-to-agent and agent-to-system communication
• Communication protocols, standards, and semantic interoperability
• Integration with enterprise platforms, APIs, databases, and tools
• Authentication, authorization, access control, and identity management

Multi-Agent Coordination and Distributed Decision-Making in Organizations

• Distributed planning, problem-solving, and decision-making
• Task allocation, scheduling, and resource allocation
• Negotiation, consensus, coalition formation, and conflict resolution
• Coordination under uncertainty, incentive mechanisms, and emergent organizational behavior

Human–Agent Collaboration in Organizational Settings

• Delegation, team adaptation, and socio-technical dynamics
• Human–agent teams and hybrid intelligence
• Human-in-the-loop, human-on-the-loop, and mixed-initiative workflows
• Allocation of roles, tasks, decision rights, and responsibilities between humans and agents

Organizational Learning, Agent Adaptation, Memory, and Knowledge Management

• Continual, collaborative learning
• Agent adaptation, personalization, and context awareness
• Individual, shared, episodic, and organizational memory
• Organizational knowledge creation, transfer, retention, retrieval, and reuse
• Knowledge graphs, retrieval-augmented systems, and cross-agent learning

Governance, Accountability, and Compliance of Agents

• Governance models for agentic and multi-agent ecosystems in organizations
• Allocation of responsibility, accountability, authority, and liability
• Regulatory compliance, standards alignment

Trust, Safety, Security, Privacy, and Reliability of Agentic Systems in Organizations

• Robustness, resilience, transparency, explainability, and uncertainty awareness
• Privacy-preserving agent interaction and organizational data protection
• Detection and mitigation of cascading, and systemic failures

Evaluation, Benchmarking

• Evaluation frameworks, benchmarks, datasets, simulations, and organizational testbeds
• Metrics for agent autonomy, coordination, alignment, reliability, and safety
• Evaluation of human–agent and multi-agent team performance
• Organizational productivity, quality, cost

Organizational Design and Socio-Technical Transformation

• Effects of agentic systems on organizational structures
• Organizational readiness, adoption, and change management
• Institutional implications and the evolving role of human expertise

Applications and Deployment of Agentic Systems in Organizations

• Agentic systems in public-, private-, and nonprofit-sector organizations
• Applications in government, healthcare, education, finance, and manufacturing
• Organizational case studies, field experiments, and deployment experiences
• Adoption barriers, scaling challenges, implementation practices, and lessons learned

Submission Guidelines

Topics may include theoretical contributions, architectures, methodologies, evaluation frameworks, industrial case studies, public sector case studies, or visionary perspectives. The workshop solicits: Full research papers, short papers, Position papers, Practical papers. We invite submissions in the following categories:

• Full Research Papers: Original, unpublished research contributions presenting thorough theoretical or empirical results (maximum 16 pages excluded references)
• Short Papers: Work-in-progress, novel concepts, or preliminary experimental evaluations. (maximum 8 pages excluded references)

Authors are invited to follow the Springer Lecture Notes in Computer Science (LNCS) formatting requirements.

Review process

Submissions will be reviewed by at least two reviewers. Papers must be fully anonymised prior to submission by removing all author names, affiliations, and identifying references. At least one author of each accepted paper is required to register for the workshop and for PRIMA 2026.

Where to submit

Submission link: XXX

NOTE: AI Policy & Ethics Guidelines

MASO 2026 adheres strictly to the generative AI policy established by the main PRIMA 2026 conference. Authors may use Generative AI tools (e.g., LLMs) solely to assist with language editing, grammar refinement, or as part of a declared research methodology. Generative AI tools cannot be listed as co-authors. Authors remain fully responsible and accountable for the original intellectual content, scientific accuracy, and authenticity of their submissions. Any substantive assistance from generative AI must be explicitly disclosed upon paper submission.