Integrated sensing and communication (ISAC) in dense multi-cell networks suffers from severe inter-cell interference, degrading both sensing and communication performance. Conventional strategies focus on interference suppression. To address this issue, this paper proposed an interference empowering precoding (IEP) framework that exploits informative inter-cell interference as a distributed sensing resource while protecting communication quality-of-service (QoS) in ISAC. IEP operates on two timescales. In the slow timescale, a lightweight Transformer-based module infers the symbol-level knowledge coefficients of interfering waveforms while per-resource-element adaptation between constructive interference exploitation for sensing and robust suppression for communication is conducted in the fast timescale. A joint optimization problem was formulated to maximize the weighted sum of the communication sum rate and the log-determinant of Fisher Information Matrix with QoS and constructive interference alignment constraints under channel state information uncertainty. The non-convex problem is reformulated as a difference-of-convex program and solved using an alternating Weighted Minimum Mean Square Error and Convex-Concave Procedure algorithm with guaranteed convergence. Simulation results demonstrate that the proposed framework could sub-stantially enlarge the achievable communication-sensing trade-off region. Notably, it achieves approximately 24% reduction in the Position Error Bound and a 21.5% extension in detection range compared to conventional interference suppression schemes, without compromising communication throughput.

Code-hopping multiple access (CHMA) technology is an effective approach for improving the user capacity of direct sequence spread spectrum systems. However, the use of randomly generated code-hopping (CH) patterns in a typical CHMA system often causes code collisions that severely degrade the bit error rate (BER) performance. Our previous work has developed a CH pattern design method to improve the BER performance of complementary coded CHMA (CC-CHMA) by pre-generating well-designed CH patterns. However, this method is mainly applicable to single-path channels, while detecting collisions and taking appropriate actions in complex multipath channels remains challenging. In this work, we present a collision-aware algorithm and propose a CH pattern update algorithm based on multi-agent reinforcement learning for CC-CHMA in uplink multipath channels. The simulation results show that the proposed CH pattern design scheme can automatically adapt to the uplink multipath channels and effectively reduce code collisions, thereby achieving further improved BER performance compared with existing CC-CHMA systems.