Call for Papers
We invite research papers, position papers, benchmark and dataset papers, and systems and demonstration reports on agentic AI in the systems that move people. Submissions are due November 20, 2026 through OpenReview.
Scope
The workshop brings together the AI agents, autonomous driving, transportation, and human-AI interaction communities around a single question:
What does it take for agentic AI to operate reliably, cooperatively, and accountably when embodied in the systems that move people?
Submissions are expected to speak to one or more of the following questions.
- Which agent designs remain effective under the grounding, latency, and safety constraints of real vehicles?
- How should mobility agents coordinate at fleet and network scales?
- How should agents interpret traveler goals, sustain calibrated trust, and adapt to the drivers, passengers, and road users around them?
- How should agentic mobility be evaluated beyond driving metrics?
We welcome theoretical, algorithmic, empirical, benchmark, systems, and position contributions.
Topics of interest
Submissions are organized around four themes. Work that spans more than one theme is welcome.
Agentic vehicles and in-cabin services
- In-vehicle copilots and driving agents built on LLM, VLM, and VLA models
- Multimodal context modeling and situational awareness across the cabin and the road scene
- Grounding language and plans in vehicle perception and control
- World models of traffic scenes
- Memory, reflection, and tool use at latencies that vehicles require
- Degrees of vehicle agency
Agentic fleets, transit, and traffic
- Robotaxi dispatch and rebalancing
- Agentic orchestration of ride-hailing, transit, curbside, charging, and logistics
- Negotiation among vehicle, infrastructure, and traffic management agents
- Multi-agent reinforcement learning and LLM-based reasoning at network scale
- Generative-agent simulation of travelers and cities
Travelers, drivers, and road users
- Interpreting and negotiating trip goals in natural language
- Driver and traveler state understanding
- Explanation and theory of mind in the cabin
- Personalization and long-term memory of traveler preferences
- Trust calibration in and around automated vehicles
- Accessibility
- Communication with pedestrians and other road users
Key question: how should a mobility agent act when a traveler's inferred goals and stated instructions conflict?
Trustworthy deployment on real roads
- Benchmarks that measure mobility agency beyond driving metrics
- Road safety consequences of hallucination, goal drift, and adversarial manipulation
- Verification, runtime assurance, and staged rollout of services at city scale
- Alignment with traveler and societal values
- Privacy and accountability in deployed mobility services
Submission types and format
Contribution types
- Research papers
- Position, benchmark, or dataset papers
- Systems and demonstration reports
Format
Submissions are limited to 4 pages excluding references and must use the AAAI-27 author kit format. Submissions may present unpublished work, work in progress, work concurrently submitted elsewhere, or recently published work.
Presentation and publication
The workshop is non-archival. Working notes of accepted papers will be posted on the workshop website with author consent. Most accepted papers will be presented as posters in one of two poster sessions, and a smaller number will be selected as spotlight talks in the themed session that matches their topic. The poster sessions have a mentoring focus and are designed to give students and junior researchers a supportive setting to present their work.
Authors of the strongest contributions will be invited to submit extended versions to the journal Artificial Intelligence for Transportation.
Work at an early stage, position papers, benchmark proposals, and negative results are explicitly welcome.
Review process
Reviewing is double-blind and handled through OpenReview. The submission link will be announced on this page. Each submission receives at least two reviews, and we target three.
Reviewers assess relevance to the workshop theme, technical soundness, originality, and the potential to prompt discussion at the workshop.
Submissions and reviews remain private. Only the working notes of accepted papers are posted, and only with author consent.
We expect at least one author of each accepted paper to register for and attend the workshop in person. The workshop is held in person only, and no virtual presentations will be offered, in line with AAAI-27 policy.
The workshop follows the AAAI-27 policy on the use of large language models.
Organizers and people with a personal conflict of interest with an organizer do not submit papers. Conflicts of interest are enforced in OpenReview.
Important dates
- October 2, 2026Call for papers released
- November 20, 2026Submission deadline
- December 2, 2026Notification of acceptance
- January 15, 2027Talk titles and schedule posted
- February 22 or 23, 2027Workshop at AAAI-27, Montréal (one day, in person, exact day to be confirmed)
Submit
Submissions are due November 20, 2026 through OpenReview. The submission link will be posted here when it opens. Questions about scope, format, or eligibility can be sent to the organizers.
A limited number of travel grants will be available for students and authors from underrepresented groups. Details will be announced.