JCAS-MARL: Joint Communication and Sensing UAV Networks via Resource-Constrained Multi-Agent Reinforcement Learning

Collection of new arXiv papers (Mar 24, 2026) covering advances in wireless systems, distributed inference, coding theory, and privacy. Key contributions include: JCAS-MARL — a resource-aware multi-agent RL framework for joint communication-and-sensing UAV networks (OFDM pilot-density control, energy/CO2-aware states); resilient V2V jitter modeling and adaptive power/link-diversity mitigation; variable-length solid and error-detecting codes and probabilistic results on MDS/super-regular matrices; pricing and mean-field analysis for low-latency coded payload delivery (including RLNC fast lanes,