Sep 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
6G research increasingly treats vehicular communicationas an active, goal-driven substrate rather than a passivepipe for bits. This survey examines Agentic Vehicle-to-Everything(V2X) Communications, where vehicles and roadside entities actas autonomous agents that exchange information according to itsvalue toward explicit goals (goal-aware information exchange),share a common semantic picture of the driving scene (semanticcoordination), and reach distributed decisions inside explicitsafety, trust, and interoperability bounds (autonomous decisionmaking).Working from an explicit search methodology, we placethe survey against 27 related works along ten dimensions and findthat none brings these threads together within a single vehicularframework. We formalize what an agentic V2X entity is, introducea nine-criterion qualification table on which no surveyedvehicular system class scores more than four, and organize theliterature into a five-layer taxonomy that runs from 6G enablersthrough value-of-information scheduling, ontology-based semanticcoordination and negotiation, up to multi-agent reinforcementlearning (MARL) and large language model (LLM) reasoninggated by a formally scoped safety shield. Three reproduciblenumerical studies make the mechanisms concrete: value-ofinformationscheduling compared against fixed-periodicity andage-of-information baselines, the way negotiation converges asthe number of agents grows, and a control-barrier-function shieldwhose guarantee holds only within its assumed sensing bound.We propose a reference architecture, work through use cases andwhere they stop being appropriate, separate safety from securityby way of a threat taxonomy, set out a six-category evaluationtaxonomy, map standardization needs onto existing bodies, andclose with fourteen open challenges and a roadmap.
The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.
Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al.· IEEE Transactions on Softwar...· 178 citations· ⚡14
Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.
M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al.· e-Informatica Software Engin...· 157 citations· ⚡17
This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.
Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al.· Empirical Software Engineeri...· 127 citations· ⚡15
The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.
Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al.· Journal of Systems and Softw...· 111 citations· ⚡8
The ongoing work building a Raspberry Pi cluster consisting of 300 nodes is presented, with potential use cases being an inexpensive and green test bed for cloud computing research and a robust and mobile data center for operating in adverse environments.
P. Abrahamsson, S. Helmer, Nattakarn Phaphoom et al.· IEEE International Conferenc...· 110 citations· ⚡7
The results indicate that software developers are a slightly happy population, but the need for limiting the unhappiness of developers remains, and 219 factors representing causes of unhappiness while developing software are identified.
D. Graziotin, Fabian Fagerholm, Xiaofeng Wang et al.· International Conference on...· 84 citations· ⚡6
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduSep 14, 2026
The “HardFlow” algorithm could help generative AI models produce high-quality outputs that obey strict requirements when “pretty close” doesn’t cut it.
AI may appear weightless, but every model depends on physical infrastructure. To understand responsible AI, we need to look beyond algorithms and consider the entire lifecycle of the hardware behind them. The post Responsible AI Must Consider Its Afterlife appeared first on GPT-Lab.