pith. sign in

arxiv: 2507.04996 · v10 · pith:PL3XYNXCnew · submitted 2025-07-07 · 💻 cs.CY · cs.CE· cs.CL· cs.HC· cs.RO

Agentic Vehicles for Human-Centered Mobility: Definition, Prospects, and Synergistic Co-Development with Vehicle Autonomy

Jiangbo Yu , Raphael Frank , Luis Miranda-Moreno , Sasan Jafarnejad , Jonatas Augusto Manzolli , Fuqiang Liu , Jiyao Wang , Ali Eslami This is my paper

Pith reviewed 2026-05-22 00:20 UTC · model grok-4.3

classification 💻 cs.CY cs.CEcs.CLcs.HCcs.RO
keywords autonomyagencyvehiclesmobilityagenticautonomousco-developmentexternal
0
0 comments X

The pith

Autonomy concerns task execution under rules while agency enables goal-directed adaptive actions in vehicles, making them purposeful actors.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that recent advances in vehicles show capabilities like handling ambiguous goals, social engagement, and ethical reasoning that go beyond standard autonomy. It introduces the concept of agentic vehicles to capture these broader social cognitive functions for human-centered mobility. Autonomy is defined as operating according to internal rules, focusing on what to do and how, whereas agency addresses why to do it and what alternatives exist. This leads to viewing autonomy and agency as orthogonal dimensions that can be developed synergistically. The result positions vehicles not just as automated systems but as active participants in society.

Core claim

Autonomy, from the Greek roots meaning self-law, means vehicles can operate according to internal rules with minimal external control, aligning with SAE levels of automated driving. Yet capabilities such as ambiguous goal handling, purposeful social engagement, external tool use, proactive problem solving, continuous learning, and context-sensitive reasoning in unseen and ethically salient situations exceed what autonomy entails. The paper therefore defines agentic vehicles to fill this gap, arguing that autonomy and agency are intertwined but distinct: autonomy for task executions, agency for goal-directed adaptive actions. These orthogonal dimensions support co-development, with agencymark

What carries the argument

The orthogonal distinction between autonomy (internal-rule task execution) and agency (goal-directed, adaptive actions), enabling synergistic co-development for vehicle intelligence.

Load-bearing premise

That the listed capabilities like ambiguous goal handling and context-sensitive ethical reasoning are not already covered or emergent from advanced autonomous vehicle technologies.

What would settle it

A demonstration that current or near-future autonomous vehicle systems, extended only with better perception and control, can fully handle ambiguous goals, proactive social problem-solving, and ethical dilemmas without needing a distinct agency framework.

Figures

Figures reproduced from arXiv: 2507.04996 by Ali Eslami, Fuqiang Liu, Jiangbo Yu, Jiyao Wang, Jonatas Augusto Manzolli, Luis Miranda-Moreno, Raphael Frank, Sasan Jafarnejad.

Figure 1
Figure 1. Figure 1: Example scenario illustrating the distinction between autonomous vehicles (AuVs) and agentic vehicles (AgVs). When a passenger suffers a heart attack en route to a restaurant, the AuV continues on its pre-assigned route until externally redirected. In contrast, the AgV exhibits contextual reasoning, goal adjustment, and external tool use: it detects and assesses the crisis, reroutes to the nearest hospital… view at source ↗
read the original abstract

Autonomy, from the Greek autos (self) and nomos (law), refers to the capacity to operate according to internal rules without external control. Autonomous vehicles (AuVs) are therefore understood as vehicular systems that perceive their environment and execute tasks with minimal human intervention, consistent with the direction indicated by the SAE levels of automated driving. However, recent research and deployments increasingly showcase vehicular capabilities that, while not contradicting autonomy, are not entailed by it, including ambiguous goal handling, purposeful social engagement, external tool use, proactive problem solving, continuous learning, and context-sensitive reasoning in unseen and ethically salient situations, enabled in part by multimodal language models. These developments reveal a gap between technical autonomy and the broader social cognitive functions required for human-centered mobility, which are more precisely captured by the notion of agency. Therefore, rather than adding increasingly elaborate modifiers to "autonomous," we introduce agentic vehicles (AgVs) and suggest that autonomy and agency are intertwined but conceptually distinct: if autonomy concerns what to do and how to do it (task executions under internal rules), agency pertains to why to do it and what else can be done (goal-directed, adaptive actions). We present autonomy and agency as orthogonal yet synergistic dimensions with co-development implications. Vehicle agency marks a novel dimension of mobility service intelligence, heralding vehicles as purposeful actors in society.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript proposes a conceptual distinction between vehicle autonomy and agency. Autonomy is defined as the capacity to operate according to internal rules without external control, consistent with SAE levels of automated driving. Agency is positioned as capturing additional functions including ambiguous goal handling, purposeful social engagement, external tool use, proactive problem solving, continuous learning, and context-sensitive reasoning in unseen and ethically salient situations, enabled in part by multimodal language models. The paper introduces 'agentic vehicles' (AgVs) as a distinct category, argues that autonomy and agency are orthogonal yet synergistic dimensions, and discusses implications for their co-development in human-centered mobility.

Significance. If the distinction is accepted, the paper supplies a useful organizing framework for thinking about the evolution of mobility intelligence beyond task execution. It highlights the emergence of vehicles as purposeful actors and could usefully guide interdisciplinary work on AI ethics, adaptive systems, and transportation policy. The absence of empirical data or formal derivations is consistent with the paper's definitional and prospective scope.

major comments (1)
  1. Abstract: The central claim that capabilities such as 'ambiguous goal handling' and 'context-sensitive reasoning in unseen and ethically salient situations' 'are not entailed by' technical autonomy lacks explicit criteria or argumentation showing why these functions cannot be incorporated into an expanded autonomy framework that already includes learned policies, online adaptation, and multi-objective optimization. This premise is load-bearing for the necessity of introducing a separate AgV term and the asserted orthogonality of the two dimensions.
minor comments (2)
  1. The manuscript would benefit from a brief comparison with prior literature on adaptive autonomy and ethical AI in vehicles to clarify the incremental contribution of the agency framing.
  2. Some phrases (e.g., 'purposeful actors in society') could be grounded with one or two concrete mobility scenarios to improve accessibility for readers outside AI ethics.

Simulated Author's Rebuttal

1 responses · 0 unresolved

Thank you for the detailed review and for recognizing the potential of our framework for guiding interdisciplinary work on AI ethics, adaptive systems, and transportation policy. We address the major comment below and will revise the manuscript to strengthen the presentation of the conceptual distinction.

read point-by-point responses

  1. Referee: Abstract: The central claim that capabilities such as 'ambiguous goal handling' and 'context-sensitive reasoning in unseen and ethically salient situations' 'are not entailed by' technical autonomy lacks explicit criteria or argumentation showing why these functions cannot be incorporated into an expanded autonomy framework that already includes learned policies, online adaptation, and multi-objective optimization. This premise is load-bearing for the necessity of introducing a separate AgV term and the asserted orthogonality of the two dimensions.

    Authors: We thank the referee for this observation. The manuscript grounds autonomy in the etymological sense and the SAE levels as the capacity for rule-based task execution without external control. The listed capabilities are positioned as extending into open-ended social, ethical, and goal-interpretation domains that are not required by (and not typically formalized within) autonomy frameworks focused on perception, planning, and adaptation for defined tasks. We maintain that these represent orthogonal dimensions because autonomy addresses execution under internal rules while agency addresses purposeful, context-sensitive goal handling in human-centered settings. To address the concern directly, we will revise the abstract for conciseness and add explicit criteria and supporting argumentation in the introduction and conceptual framework section, drawing on distinctions from AI agency literature to show why expanded autonomy mechanisms do not automatically subsume the social-cognitive functions without diluting the utility of the separation. revision: yes

Circularity Check

0 steps flagged

No significant circularity; the argument is definitional and draws on external concepts

full rationale

The paper defines autonomy via etymology and SAE alignment as operation under internal rules with minimal intervention, then introduces agency to cover additional capabilities (ambiguous goal handling, social engagement, tool use, proactive solving, learning, context-sensitive ethical reasoning) enabled by multimodal LMs. These are presented as not entailed by the autonomy definition, leading to the orthogonal AgV concept. No equations, fitted parameters, or predictions appear. The distinction relies on conceptual separation and external observations rather than self-referential reduction, self-citation chains, or renaming of known results. The derivation remains self-contained against external benchmarks like SAE levels and established AI agency literature.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim depends on a domain assumption about the limited scope of technical autonomy and introduces a new conceptual entity without independent empirical validation or falsifiable predictions.

axioms (1)
  • domain assumption Autonomy refers to the capacity to operate according to internal rules without external control, as indicated by SAE levels of automated driving.
    This definition is used as the baseline to identify a gap that agency is meant to fill.
invented entities (1)
  • agentic vehicles (AgVs) no independent evidence
    purpose: To capture broader social cognitive functions and goal-directed behaviors in vehicles beyond technical autonomy.
    New term and category introduced to address the identified conceptual gap.

pith-pipeline@v0.9.0 · 5822 in / 1365 out tokens · 59721 ms · 2026-05-22T00:20:43.170293+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning

    cs.AI 2026-05 unverdicted novelty 5.0

    Temporal conditioning in three LLM-based planner architectures for AV scene-to-plan reasoning yields no statistically significant gains on NLP correctness metrics but enables predictive hazard reasoning and stable cor...

Reference graph

Works this paper leans on

39 extracted references · 39 canonical work pages · cited by 1 Pith paper

  1. [1]

    Preparing a nation for autonomous vehicles: opportunities, barriers and policy recommendations,

    D. J. Fagnant and K. Kockelman, “Preparing a nation for autonomous vehicles: opportunities, barriers and policy recommendations,” Transp. Res. Part Policy Pract., vol. 77, pp. 167–181, July 2015, doi: 10.1016/j.tra.2015.04.003

    work page doi:10.1016/j.tra.2015.04.003 2015

  2. [2]

    Autonomous Vehicles: Moral dilemmas and adoption incentives,

    E. Feess and G. Muehlheusser, “Autonomous Vehicles: Moral dilemmas and adoption incentives,” Transp. Res. Part B Methodol., vol. 181, p. 102894, Mar. 2024, doi: 10.1016/j.trb.2024.102894

    work page doi:10.1016/j.trb.2024.102894 2024

  3. [3]

    Talking about automated vehicles: What do levels of automation do?,

    D. Hopkins and T. Schwanen, “Talking about automated vehicles: What do levels of automation do?,” Technol. Soc., vol. 64, p. 101488, Feb. 2021, doi: 10.1016/j.techsoc.2020.101488

    work page doi:10.1016/j.techsoc.2020.101488 2021

  4. [4]

    Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey,

    D. B. Acharya, K. Kuppan, and B. Divya, “Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey,” IEEE Access, vol. 13, pp. 18912–18936, 2025, doi: 10.1109/access.2025.3532853

    work page doi:10.1109/access.2025.3532853 2025

  5. [5]

    Preparing for an agentic era of human-machine transportation systems: Opportunities, challenges, and policy recommendations,

    J. Yu, “Preparing for an agentic era of human-machine transportation systems: Opportunities, challenges, and policy recommendations,” Transp. Policy, vol. 171, pp. 78–97, Sept. 2025, doi: 10.1016/j.tranpol.2025.05.030

    work page doi:10.1016/j.tranpol.2025.05.030 2025

  6. [6]

    Sex and social representations of aggression: A communal-agentic analysis,

    A. Campbell, S. Muncer, and B. Gorman, “Sex and social representations of aggression: A communal-agentic analysis,” Aggress. Behav., vol. 19, no. 2, pp. 125–135, 1993, doi: 10.1002/1098-2337(1993)19:2<125::aid- ab2480190205>3.0.co;2-1

    work page doi:10.1002/1098-2337(1993)19:2 1993

  7. [7]

    Locus of control, altruism and agentic disposition,

    G. A. Guagnano, “Locus of control, altruism and agentic disposition,” Popul. Environ., vol. 17, no. 1, pp. 63– 77, Sept. 1995, doi: 10.1007/bf02208278

    work page doi:10.1007/bf02208278 1995

  8. [8]

    doi:10.1037/0022- 3514.50.2.229

    G. S. Howard and P. R. Myers, “Predicting human behavior: Comparing idiographic, nomothetic, and agentic methodologies.,” J. Couns. Psychol., vol. 37, no. 2, pp. 227–233, Apr. 1990, doi: 10.1037/0022- 0167.37.2.227

    work page doi:10.1037/0022- 1990

  9. [9]

    Generative AI Meets Service Robots,

    J. Wirtz and R. Stock-Homburg, “Generative AI Meets Service Robots,” J. Serv. Res., May 2025, doi: 10.1177/10946705251340487

    work page doi:10.1177/10946705251340487 2025

  10. [10]

    Self-driving cars: A survey,

    C. Badue et al., “Self-driving cars: A survey,” Expert Syst. Appl., vol. 165, p. 113816, Mar. 2021, doi: 10.1016/j.eswa.2020.113816

    work page doi:10.1016/j.eswa.2020.113816 2021

  11. [11]

    A survey of deep learning techniques for autonomous driving,

    S. Grigorescu, B. Trasnea, T. Cocias, and G. Macesanu, “A survey of deep learning techniques for autonomous driving,” J. Field Robot., vol. 37, no. 3, pp. 362–386, Apr. 2020, doi: 10.1002/rob.21918

    work page doi:10.1002/rob.21918 2020

  12. [12]

    Deep Reinforcement Learning for Autonomous Driving: A Survey,

    B. R. Kiran et al., “Deep Reinforcement Learning for Autonomous Driving: A Survey,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 6, pp. 4909–4926, June 2022, doi: 10.1109/tits.2021.3054625

    work page doi:10.1109/tits.2021.3054625 2022

  13. [13]

    Lidar for Autonomous Driving: The Principles, Challenges, and Trends for Automotive Lidar and Perception Systems,

    Y. Li and J. Ibanez-Guzman, “Lidar for Autonomous Driving: The Principles, Challenges, and Trends for Automotive Lidar and Perception Systems,” IEEE Signal Process. Mag., vol. 37, no. 4, pp. 50–61, July 2020, doi: 10.1109/msp.2020.2973615

    work page doi:10.1109/msp.2020.2973615 2020

  14. [14]

    Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review,

    D. J. Yeong, G. Velasco-Hernandez, J. Barry, and J. Walsh, “Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review,” Sensors, vol. 21, no. 6, p. 2140, Mar. 2021, doi: 10.3390/s21062140

    work page doi:10.3390/s21062140 2021

  15. [15]

    A Survey of Autonomous Driving: Common Practices and Emerging Technologies,

    E. Yurtsever, J. Lambert, A. Carballo, and K. Takeda, “A Survey of Autonomous Driving: Common Practices and Emerging Technologies,” IEEE Access, vol. 8, pp. 58443–58469, 2020, doi: 10.1109/access.2020.2983149

    work page doi:10.1109/access.2020.2983149 2020

  16. [16]

    Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges,

    D. Feng et al., “Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 3, pp. 1341–1360, Mar. 2021, doi: 10.1109/tits.2020.2972974

    work page doi:10.1109/tits.2020.2972974 2021

  17. [17]

    An Overview of Recent Advances in Coordinated Control of Multiple Autonomous Surface Vehicles,

    Z. Peng, J. Wang, D. Wang, and Q.-L. Han, “An Overview of Recent Advances in Coordinated Control of Multiple Autonomous Surface Vehicles,” IEEE Trans. Ind. Inform., vol. 17, no. 2, pp. 732–745, Feb. 2021, doi: 10.1109/tii.2020.3004343

    work page doi:10.1109/tii.2020.3004343 2021

  18. [18]

    Improving Infrastructure and Community Resilience with Shared Autonomous Electric Vehicles (SAEV-R),

    J. Yu, M. F. Hyland, and A. Chen, “Improving Infrastructure and Community Resilience with Shared Autonomous Electric Vehicles (SAEV-R),” in 2023 IEEE Intelligent Vehicles Symposium (IV), Anchorage, AK, USA: IEEE, June 2023, pp. 1–6. doi: 10.1109/iv55152.2023.10186785

    work page doi:10.1109/iv55152.2023.10186785 2023

  19. [19]

    Coordinated flow model for strategic planning of autonomous mobility-on-demand systems,

    J. Yu and M. F. Hyland, “Coordinated flow model for strategic planning of autonomous mobility-on-demand systems,” Transp. Transp. Sci., vol. 21, no. 2, p. 2253474, May 2025, doi: 10.1080/23249935.2023.2253474

    work page doi:10.1080/23249935.2023.2253474 2025

  20. [20]

    Autonomous automobilities: The social impacts of driverless vehicles,

    D. Bissell, T. Birtchnell, A. Elliott, and E. L. Hsu, “Autonomous automobilities: The social impacts of driverless vehicles,” Curr. Sociol., vol. 68, no. 1, pp. 116–134, Jan. 2020, doi: 10.1177/0011392118816743

    work page doi:10.1177/0011392118816743 2020

  21. [21]

    The politics of autonomous vehicles,

    J. Stilgoe and M. Mladenović, “The politics of autonomous vehicles,” Humanit. Soc. Sci. Commun., vol. 9, no. 1, Dec. 2022, doi: 10.1057/s41599-022-01463-3

    work page doi:10.1057/s41599-022-01463-3 2022

  22. [22]

    Autonomous Vehicles That Interact With Pedestrians: A Survey of Theory and Practice,

    A. Rasouli and J. K. Tsotsos, “Autonomous Vehicles That Interact With Pedestrians: A Survey of Theory and Practice,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 3, pp. 900–918, Mar. 2020, doi: 10.1109/tits.2019.2901817. Agentic Vehicle Yu, 2025 12

    work page doi:10.1109/tits.2019.2901817 2020

  23. [23]

    A generalized diffusion model for preference and response time: Application to ordering mobility-on-demand services,

    J. Yu and M. F. Hyland, “A generalized diffusion model for preference and response time: Application to ordering mobility-on-demand services,” Transp. Res. Part C Emerg. Technol., vol. 121, p. 102854, Dec. 2020, doi: 10.1016/j.trc.2020.102854

    work page doi:10.1016/j.trc.2020.102854 2020

  24. [24]

    Drive Like a Human: Rethinking Autonomous Driving with Large Language Models,

    D. Fu et al., “Drive Like a Human: Rethinking Autonomous Driving with Large Language Models,” in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Waikoloa, HI, USA: IEEE, Jan. 2024, pp. 910–919. doi: 10.1109/wacvw60836.2024.00102

    work page doi:10.1109/wacvw60836.2024.00102 2024

  25. [25]

    A Survey on Multimodal Large Language Models for Autonomous Driving,

    C. Cui et al., “A Survey on Multimodal Large Language Models for Autonomous Driving,” presented at the Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 958–979. Accessed: July 07, 2025. [Online]. Available: https://openaccess.thecvf.com/content/WACV2024W/LLVM- AD/html/Cui_A_Survey_on_Multimodal_Large_Language_Mod...

    work page 2024

  26. [26]

    VistaGPT: Generative Parallel Transformers for Vehicles With Intelligent Systems for Transport Automation,

    Y. Tian et al., “VistaGPT: Generative Parallel Transformers for Vehicles With Intelligent Systems for Transport Automation,” IEEE Trans. Intell. Veh., vol. 8, no. 9, pp. 4198–4207, Sept. 2023, doi: 10.1109/tiv.2023.3307012

    work page doi:10.1109/tiv.2023.3307012 2023

  27. [27]

    ChatGPT as Your Vehicle Co-Pilot: An Initial Attempt,

    S. Wang, Y. Zhu, Z. Li, Y. Wang, L. Li, and Z. He, “ChatGPT as Your Vehicle Co-Pilot: An Initial Attempt,” IEEE Trans. Intell. Veh., vol. 8, no. 12, pp. 4706–4721, Dec. 2023, doi: 10.1109/tiv.2023.3325300

    work page doi:10.1109/tiv.2023.3325300 2023

  28. [28]

    Synthetic multi-criteria decision analysis (S-MCDA): A new framework for participatory transportation planning,

    J. A. Manzolli, J. Yu, and L. Miranda-Moreno, “Synthetic multi-criteria decision analysis (S-MCDA): A new framework for participatory transportation planning,” Transp. Res. Interdiscip. Perspect., vol. 31, p. 101463, May 2025, doi: 10.1016/j.trip.2025.101463

    work page doi:10.1016/j.trip.2025.101463 2025

  29. [29]

    Synthetic Participatory Planning of Shared Automated Electric Mobility Systems,

    J. Yu and G. McKinley, “Synthetic Participatory Planning of Shared Automated Electric Mobility Systems,” Sustainability, vol. 16, no. 13, p. 5618, June 2024, doi: 10.3390/su16135618

    work page doi:10.3390/su16135618 2024

  30. [30]

    Modular AI agents for transportation surveys and interviews: Advancing engagement, transparency, and cost efficiency,

    J. Yu, J. Zhao, L. Miranda-Moreno, and M. Korp, “Modular AI agents for transportation surveys and interviews: Advancing engagement, transparency, and cost efficiency,” Commun. Transp. Res., vol. 5, p. 100172, Dec. 2025, doi: 10.1016/j.commtr.2025.100172

    work page doi:10.1016/j.commtr.2025.100172 2025

  31. [31]

    AI Agents as Team Members: Effects on Satisfaction, Conflict, Trustworthiness, and Willingness to Work With,

    A. R. Dennis, A. Lakhiwal, and A. Sachdeva, “AI Agents as Team Members: Effects on Satisfaction, Conflict, Trustworthiness, and Willingness to Work With,” J. Manag. Inf. Syst., vol. 40, no. 2, pp. 307–337, Apr. 2023, doi: 10.1080/07421222.2023.2196773

    work page doi:10.1080/07421222.2023.2196773 2023

  32. [32]

    What factors contribute to the acceptance of artificial intelligence? A systematic review,

    S. Kelly, S.-A. Kaye, and O. Oviedo-Trespalacios, “What factors contribute to the acceptance of artificial intelligence? A systematic review,” Telemat. Inform., vol. 77, p. 101925, Feb. 2023, doi: 10.1016/j.tele.2022.101925

    work page doi:10.1016/j.tele.2022.101925 2023

  33. [33]

    OpenAGI: When LLM Meets Domain Experts,

    Y. Ge et al., “OpenAGI: When LLM Meets Domain Experts,” Adv. Neural Inf. Process. Syst., vol. 36, pp. 5539–5568, Dec. 2023

    work page 2023

  34. [34]

    Large Language Model-Empowered Bayesian Inference of Traveler Mental State Dynamics: A Case Study of Driver Fatigue Estimation,

    Y. Jiao, L. F. Miranda-Moreno, and J. (Gabe) Yu, “Large Language Model-Empowered Bayesian Inference of Traveler Mental State Dynamics: A Case Study of Driver Fatigue Estimation,” 2025, Elsevier BV. doi: 10.2139/ssrn.5256471

    work page doi:10.2139/ssrn.5256471 2025

  35. [35]

    LLM Multimodal Traffic Accident Forecasting,

    I. De Zarzà, J. De Curtò, G. Roig, and C. T. Calafate, “LLM Multimodal Traffic Accident Forecasting,” Sensors, vol. 23, no. 22, p. 9225, Nov. 2023, doi: 10.3390/s23229225

    work page doi:10.3390/s23229225 2023

  36. [36]

    Automating traffic model enhancement with AI research agent,

    X. Guo, X. Yang, M. Peng, H. Lu, M. Zhu, and H. Yang, “Automating traffic model enhancement with AI research agent,” Transp. Res. Part C Emerg. Technol., vol. 178, p. 105187, Sept. 2025, doi: 10.1016/j.trc.2025.105187

    work page doi:10.1016/j.trc.2025.105187 2025

  37. [37]

    What matters in AI-supported learning: A study of human-AI interactions in language learning using cluster analysis and epistemic network analysis,

    X. Wang et al., “What matters in AI-supported learning: A study of human-AI interactions in language learning using cluster analysis and epistemic network analysis,” Comput. Educ., vol. 194, p. 104703, Mar. 2023, doi: 10.1016/j.compedu.2022.104703

    work page doi:10.1016/j.compedu.2022.104703 2023

  38. [38]

    Interpretable State-Space Model of Urban Dynamics for Human-Machine Collaborative Transportation Planning,

    J. Yu and M. F. Hyland, “Interpretable State-Space Model of Urban Dynamics for Human-Machine Collaborative Transportation Planning,” Transp. Res. Part B Methodol., vol. 192, p. 103134, Feb. 2025, doi: 10.1016/j.trb.2024.103134

    work page doi:10.1016/j.trb.2024.103134 2025

  39. [39]

    Bots with Feelings: Should AI Agents Express Positive Emotion in Customer Service?,

    E. Han, D. Yin, and H. Zhang, “Bots with Feelings: Should AI Agents Express Positive Emotion in Customer Service?,” Inf. Syst. Res., vol. 34, no. 3, pp. 1296–1311, Sept. 2023, doi: 10.1287/isre.2022.1179

    work page doi:10.1287/isre.2022.1179 2023