This survey traces the evolution from LM-driven SemCom to TokenCom, and examines the token abstraction, the transmission techniques it requires, and two emerging paradigms, namely TokenCom for LM services and for embodied and agentic intelligence.
Abstract
The ambitious requirements of sixth-generation (6G) networks are driving communication systems from reliable bit delivery toward meaning-aware and task-oriented connectivity. Large models (LMs), with strong multimodal understanding and generation capabilities, have accelerated this shift and made semantic communication (SemCom) increasingly practical. Yet current LM-driven SemCom remains fragmented: semantic representations are typically tied to specific modalities, models, or tasks. While the bit provides a universal unit for digital transport, there is still no analogous unit for representing and processing semantics, which limits interoperability, theoretical unification, and scalable system design. We argue that tokens provide a natural candidate for this missing abstraction. Two trends support this: unified multimodal LMs now encode text, images, audio, video, and robot actions in one token space, while distributed LM inference already generates substantial token-level traffic through expert routing, cache transfer, and speculative decoding. Token communication (TokenCom) emerges by unifying these trends, using the LM's native processing unit as a communication abstraction above the bit level and enabling importance assignment, error handling, and resource allocation directly at token granularity. This survey traces the evolution from LM-driven SemCom to TokenCom. We review three major directions of LM-driven SemCom: source-centric semantic coding, channel semantics for physical-layer tasks, and collaborative edge-device intelligence. We then examine the token abstraction, the transmission techniques it requires, and two emerging paradigms, namely TokenCom for LM services and for embodied and agentic intelligence. Finally, we identify open challenges toward unified, scalable, and AI-native 6G communication systems.
A two-axis taxonomy connecting six compression families to five semantic communication architectures is synthesized with a quantitative meta-analysis of the model-size-versus-semantic-fidelity Pareto frontier, synthesized with a quantitative meta-analysis of the model-size-versus-semantic-fidelity Pareto frontier.
Srikanth Kamath, A. Mathur, Joslyn Sajan George et al.· 0 citations
Collaborative embodied artificial intelligence (CEAI) enables multiple physical agents to perceive, reason, and act cooperatively in dynamic environments. Effective communication is essential for CEAI, yet CEAI agents must exchange not only large multimodal observations but also task-relevant insights, intents, and int...
Multimodal semantic communication reduces uplink overhead by transmitting compact task-relevant representations. However, existing token compression methods either aggregate tokens using fixed structures or select tokens under fixed modality-wise budgets, without jointly adapting modality relevance and token utility to...
ComVLA is proposed, a framework that uses the dense semantic information contained in the language guidance to adapt the VLA token budget to the channel capacity, and demonstrates that co-designing VLA inference and wireless communication is a practical direction for 6G-connected robotics.
Bo-Liang Liu, Wint Yi Poe, Jing-Yun Di et al.· 0 citations
This PRISMA-based review examines how goal-oriented semantics, knowledge graphs, and LLMs shape representation, compression, and task quality under rate and latency constraints across UAVs, NTNs, ISAC, Metaverse, and IoT.
Sushil Kumar Singh, Danish Ali, Muhammad Talha Usman et al.· ICCK Transactions on Sensing...· 2 citations
Sixth-generation (6G) applications are increasingly requiring receivers to execute tasks based on received information. However, existing approaches optimize bit-level reconstruction independently of task relevance, so scarce transmission resources can be spent on task-irrelevant information, making the resulting data...
Joonho Seon, Seongwoo Lee, Soohyun Kim et al.· IEEE Communications Surveys...· 0 citations
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.