Submission Deadline: May 22, 2026, Anywhere on Earth
Author Notification: June 12, 2026
This workshop targets AI/ML researchers, data scientists, software engineers, and enterprise AI practitioners working on:
Agent architectures and systems, e.g., multi-agent frameworks, memory systems, and skill-based agent design
Enterprise applications and deployments, e.g., real-world case studies and infrastructure for agents from industry
Evaluation and governance, e.g., benchmarks and trust mechanisms
We welcome participation from academia, industry, and government to foster cross-disciplinary collaboration!
We encourage all submissions related to LLM usage in an enterprise setting, with a special focus on, but not limited to, the following topics:
Multi-agent system design, coordination, and orchestration for enterprise applications, including task planning and workflow management
Memory and state management for long-running enterprise AI agents
LLM and AI agent usage in dynamic enterprise environments (e.g., supply chain, IT operations)
Post-training and alignment techniques for enterprise AI agents, including reinforcement learning with verifiable or programmatic rewards (e.g., RLVR)
Data flywheels and feedback-driven learning for enterprise AI agents, including post-deployment refinement based on evaluation signals and user or system feedback
Synthetic data generation for training and evaluating enterprise AI agents in data-scarce or sensitive domains
Evaluation frameworks, benchmarks, and methodologies for enterprise AI agents
Observability, monitoring, and debugging of enterprise AI agents, including tracing, logging, and failure analysis
Cost, latency, and resource optimization for large-scale enterprise AI agent systems
Deployment platforms and system architectures for enterprise AI agents
Low-code and no-code interfaces for building and operating enterprise AI agents by non-technical users
Human-in-the-loop design, escalation policies, and controllability for enterprise AI agents
Red-teaming, adversarial testing, and robustness evaluation for enterprise AI agents
Security, privacy, governance, and trustworthiness in enterprise agentic systems
All submissions must be in a single PDF file and formatted using the Standard ACM Conference Proceedings Template. Supplementary materials such as demonstration videos, datasets, and code may be included either as additional files or via external links within the PDF.
All accepted papers will be presented as posters. Depending on the schedule, some will also be selected for oral presentations. Submissions will be evaluated based on quality, novelty, impact, depth, clarity, and generalizability. For each accepted paper, at least one author must attend the workshop and present it.
We accept three types of paper submissions:
Track 1: Full length papers. Submissions in this track can be up to 6 pages, plus any pages of additional references and appendices.
Track 2: Demonstration. Submission for this track can be up to 4 pages, plus any pages of additional references and appendices. This track is for software demonstration proposals that describe agentic AI usage in Enterprise setting. The submitted proposal should include architecture of the proposed system, supported functionalities, user scenarios, interface and interaction options, etc. The submission of a demonstration video (up to 5 minutes and 50MB) together with your demonstration proposal is encouraged.
Track 3: Extended abstract. Submission for this track can be up to 2 pages, plus any pages of additional references and appendices. For this track, we encourage submissions that describe visionary ideas, preliminary results, controversial findings, or experience sharing.
Authors should note that reviewers are not required to read appendices. Previously submitted or published work is acceptable. Authors are responsible for ensuring compliance with the policies of other venues.
Reviews are single-blind. Feel free to include author names and affiliations in your submission.ย
Submition link will be posted shortly.