Benchmarking & evaluation
Datasets, metrics, and realistic enterprise task environments for performance, safety, and reliability.
NeurIPS 2026 Workshop · AABA4ET
2nd Workshop on Agentic AI Benchmarks and Applications for Enterprise Tasks
Where Agentic AI meets the real world of work
Benchmarking, evaluating, and deploying intelligent agents for complex enterprise operations at scale.
Update
Accepted for NeurIPS 2026 — submissions open through August 31, 2026 (AoE).
About the workshop
Bridge research and enterprise deployment
Foster collaboration toward robust, efficient, and trustworthy Agentic AI for complex, dynamic enterprise operations.
The 2nd Workshop on Agentic AI Benchmarks and Applications for Enterprise Tasks continues the AAAI 2026 edition in Singapore. We connect cutting-edge agent research with the practical demands of evaluation and real-world deployment.
Focus areas
What we want to discuss
Original work across benchmarking, applications, safety, and multi-agent systems in enterprise settings.
Enterprise applications
On-site understanding, planning, observation, reflection, and system management in business contexts.
Safety & trustworthiness
Failure recovery, distribution shift, guardrails, and trust for long-running production agents.
Human–agent interaction
Assistants that augment people inside real enterprise workflows.
Multimodal reasoning
Vision, text, and audio for robust decision-making in physical enterprise data.
Planning & orchestration
Multi-agent and tool strategies for complex, multi-step enterprise goals.
Important dates
Mark your calendar
All deadlines are Anywhere on Earth (AoE).
Aug 31, 2026
Submission deadline
Sep 29, 2026
Acceptance notification
Dec 11–12, 2026
Workshop day (TBD)
Call for papers
4 pages · NeurIPS style · non-archival
Double-blind review. Dual submission welcome. At least one author must present in person.