An Embodied Multiagent Framework Based on Token Communications for Cooperative ISAC

Jiahe Guo; Jun Du; Chunxiao Jiang; Jintao Wang

eess.SPOct 8, 2026

An Embodied Multiagent Framework Based on Token Communications for Cooperative ISAC

Authors: Jiahe Guo, Jun Du, Chunxiao Jiang, Jintao Wang

Organizations: Department of Electronic Engineering, Tsinghua University, Beijing 100084, China · State Key Laboratory of Space Network and Communications, Tsinghua University, Beijing 100084, China · Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China

Abstract

The emerging low-altitude economy demands unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) for reliable connectivity and environmental awareness. In particular, embodied UAV agents offer a promising means of supporting autonomous operations through a closed loop linking perception, decision-making, and physical actions. However, each UAV has access only to local observations, and effective cooperation requires exchanging local states and intentions. Directly sharing such information can incur substantial signaling overhead and hinder timely coordination in dynamic environments. To deal with this problem, this paper investigates a cooperative ISAC network of embodied UAV agents and formulates a joint token communications (TokCom) and physical control problem to minimize total propulsion energy subject to communication and sensing rate requirements. Then, we propose a state--intent TokCom (SI-TokCom) framework driven by multi-agent embodied policy learning. Specifically, separate pretrained codebooks enable compact exchanges of local states and intentions, while UAV agents jointly learn to select and compose tokens and determine physical actions based on local observations and received tokens. Simulation results show that SI-TokCom achieves 98.9% and 99.1% of the centralized baseline's communication and sensing rates, respectively. Compared with the local baseline, it improves the corresponding rates by 5.0% and 43.6%, respectively, with essentially unchanged propulsion energy. These results highlight the potential of TokCom for communication-efficient cooperation among embodied UAV agents in ISAC systems.

Figures & tables

Fig. 1: Cooperative multi-UAV ISAC system.

Fig. 2: Slot-level cooperative protocol for the multi-UAV ISAC system.

Fig. 3: Overview of the proposed framework with offline codebook pretraining and online joint optimization.

\bm{\varphi}_{r}[t]=\begin{cases}\sum_{j=1}^{N_{s}}\omega_{1}\alpha_{k,i}[t]b_{k,i}[t]\sqrt{1+\mu_{j}^{s}}\sqrt{G_{p}}\left(\rho_{k,j}^{s}\right)^{*}\left(\xi_{j,r}^{s}\right)^{*}\mathbf{a}_{k,j}^{s}+\omega_{2}b_{k,i}[t]\sqrt{1+\mu^{c}}\left(\xi^{c}\right)^{*}\mathbf{h}_{k,i}^{c},r=1,\\ \sum_{j=1}^{N_{s}}\omega_{1}\alpha_{k,i}[t]b_{k,i}[t]\sqrt{1+\mu_{j}^{s}}\sqrt{G_{p}}\left(\rho_{k,j}^{s}\right)^{*}\left(\xi_{j,r}^{s}\right)^{*}\mathbf{a}_{k,j}^{s},r=2,\ldots,N_{s}+1\end{cases}.

(27)

Table 4

Parameter	Value	Parameter	Value
$K,\,N_{c},\,N_{s}$	$4,\,8,\,3$	$w_{\rm c},\,w_{\rm s},\,w_{\rm E}$	$0.6,\,0.4,\,0.8$
$H$	$80~\mathrm{m}$	$\omega_{1},\,\omega_{2}$	$0.4,\,0.6$
$N_{T},\,T$	$12,\,1~\mathrm{s}$	$L_{\rm in},\,L_{\rm out}$	$20,\,8$
$V_{k}^{\max}$	$15~\mathrm{m/s}$	FP–KKT tolerance	$10^{-3}$
$D_{\min}$	$20~\mathrm{m}$	$N_{\mathrm{S}}^{\rm tok},\,N_{\mathrm{I}}^{\rm tok}$	$64,\,64$
$M$	$4$	$D_{\mathrm{S}}^{\rm tok},\,D_{\mathrm{I}}^{\rm tok}$	$16,\,16$

TABLE I: Main Simulation Parameters

Fig. 4: Average reward convergence of different schemes.

Scheme	Comm. rate $\uparrow$ (Mbit/s)	Sensing rate $\uparrow$ (kbit/s)	Energy $\downarrow$ (J)	Comm. QoS $\uparrow$ (%)	Sensing QoS $\uparrow$ (%)	Coord. payload (bit)
Centralized	$7.22$	$65.04$	$42.18$	$99.45$	$93.48$	—
TokenCom	$7.14$	$64.44$	$42.11$	$98.73$	$93.89$	$96$
Local	$6.80$	$44.88$	$42.11$	$99.39$	$78.91$	$0$
Intent Only	$7.06$	$58.60$	$42.16$	$98.83$	$90.91$	$78$
State Only	$6.93$	$64.93$	$42.23$	$97.96$	$92.46$	$18$
SemanticCom	$7.03$	$60.21$	$43.17$	$98.76$	$90.26$	$96$

TABLE II: Late-Stage Performance Comparison

Fig. 5: Average SPEB over all STs during training for different schemes.

Panel of Figure 9 — Fig. 6: UAV trajectories generated by TokenCom under different network sizes and randomly generated CU and ST layouts.

Fig. 7: Tradeoff between the communication and sensing rates.

Panel of Figure 11 — Fig. 8: Token usage statistics: (a), (b) usage frequencies in scenario A; (c), (d) usage-frequency differences between scenarios B and A (scenario B minus scenario A). Frequencies are expressed as percentages and differences as percentage points.

Panel of Figure 12 — Fig. 9: Terminal SPEB at $t=12$ in a sensing-only test with $N_{s}=1$ and $N_{c}=0$ : (a) spatial distribution over the ST position grid; (b) central slices at $x=300~\mathrm{m}$ (upper) and $y=300~\mathrm{m}$ (lower); and (c) empirical CDF over all sampled ST locations.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

	$\displaystyle B[t]=$	$\displaystyle\omega_{1}b_{k,i}[t]\sum_{j=1}^{N_{s}}\log\left(1+\mu_{j}^{s}\right)+\omega_{2}b_{k,i}[t]\log\left(1+\mu^{c}\right)-\omega_{1}b_{k,i}[t]\mu_{j}^{s}-\omega_{2}b_{k,i}[t]\mu^{c}$		(35)
		$\displaystyle-\omega_{2}b_{k,i}[t]\left\|\xi^{c}\right\|^{2}N_{0}b_{k,i}[t]-\omega_{1}b_{k,i}[t]\left\|\xi_{j}^{s}\right\|^{2}N_{0}b_{k,i}[t].$		(35)

Appendix

Table 13

Explore similar work

Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities
Oct 1, 2026Peng Yi, Ying-Chang LiangAgent Communication Protocols Task-Oriented Semantic Communication
National Key Laboratory of Wireless Communications, and also with the Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China · Institute of Fundamental and Frontier Sciences and the Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China
A Camera-Cooperative ISAC Framework for Multimodal Non-Cooperative UAVs Sensing
May 21, 2026Wenfeng Wu, Luping Xiang, Kun YangCamera-Radar Fusion Integrated Sensing and Communication
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, 210008, China · Institute of Intelligent Networks and Communications (NINE) and School of Intelligent Software and Engineering, Nanjing University (Suzhou Campus), Suzhou, 215163, China
When Agentic AI Meets Integrated Sensing and Communication
Aug 6, 2026Kai Li, Conggai Li, Sarah Ali Siddiqui +4Integrated Sensing and Communication AI Agent Evaluation
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg · Technology, CSIRO, Sydney, NSW, Australia · College of Computer, Qassim University, Buraydah, Saudi Arabia +1

Oct 1, 2026, eess.SPJ/K move · Enter open · S save

Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities

Peng Yi, Ying-Chang Liang

National Key Laboratory of Wireless Communications, and also with the Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China · Institute of Fundamental and Frontier Sciences and the Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China

Agent Communication Protocols Task-Oriented Semantic Communication Embodied AI Multi-Agent Communication

Open paper AskPDF arXiv

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 interactive information over long horizons. This article investigates token communication (TokCom) as a native intelligence interface for CEAI, in which tokens serve jointly as compact semantic carriers for communication and fundamental inference units for generative foundation models (GFMs). We first discuss how TokCom supports insight sharing, intent alignment, and interactive control among embodied agents. We then propose a TokCom-assisted CEAI framework driven by a task-adaptive communication protocol. Comprising a compact codebook, syntax rules, and contextual examples, this protocol guides GFM-based transceivers to distill messages into compact tokens and reconstruct them after wireless transmission. A case study on collaborative object transport demonstrates that the proposed TokCom framework substantially reduces the source payload bit consumption while preserving task efficiency and showing robustness under noisy channels. Finally, we outline future research directions.

Abstract

Explore similar work

Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities

A Camera-Cooperative ISAC Framework for Multimodal Non-Cooperative UAVs Sensing

When Agentic AI Meets Integrated Sensing and Communication