# Spatiotemporal Continual Federated Learning for Agentic Multi-UAV Edge Networks: Mitigating Catastrophic Forgetting

arXiv: https://arxiv.org/abs/2601.21861 · HTML: https://mlsanity.com/paper/2601.21861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 14 of 14)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks](https://mlsanity.com/paper/1810.10408/) (2018)
- [Cellular-Connected UAVs over 5G: Deep Reinforcement Learning for Interference Management](https://mlsanity.com/paper/1801.05500/) (2018)
- [On-Demand Density-Aware UAV Base Station 3D Placement for Arbitrarily Distributed Users with Guaranteed Data Rates](https://mlsanity.com/paper/1904.10881/) (2019)
- [Hierarchical Multi-Agent DRL Based Dynamic Cluster Reconfiguration for UAV Mobility Management](https://mlsanity.com/paper/2412.16167/) (2024)
- [UAV Swarm-enabled Collaborative Post-disaster Communications in Low Altitude Economy via a Two-stage Optimization Approach](https://mlsanity.com/paper/2501.05742/) (2025)
- [Adaptive and Fair Deployment Approach to Balance Offload Traffic in Multi-UAV Cellular Networks](https://mlsanity.com/paper/2210.16797/) (2022)
- [Continuous Transfer Learning for UAV Communication-aware Trajectory Design](https://mlsanity.com/paper/2405.10087/) (2024)
- [Cross-Domain Continual Learning for Edge Intelligence in Wireless ISAC Networks](https://mlsanity.com/paper/2502.12736/) (2025)
- [The Coverage Overlapping Problem of Serving Arbitrary Crowds in 3D Drone Cellular Networks](https://mlsanity.com/paper/2008.09519/) (2020)

## Abstract (arXiv)

This paper addresses multi-objective conflicts and catastrophic forgetting in uncrewed aerial vehicle (UAV) networks across dynamic spatiotemporal environments. Conventional multi-agent reinforcement learning (MARL) algorithms suffer from severe policy degradation during sequential task transitions. We propose a spatiotemporal continual federated learning (SCFL) framework driven by the group-decoupled multi-agent proximal policy optimization (G-MAPPO) algorithm. SCFL incorporates a three-stage geometric alignment mechanism: it resolves local gradient conflicts via group-decoupled policy optimization (GDPO), mitigates spatial Non-Independent and Identically Distributed (non-IID) client drift through adaptive cosine aggregation, and suppresses inter-task interference via global temporal orthogonal projection without raw experience replay. Evaluations show that SCFL achieves superior robustness over federated baselines, maintaining spatial service reliability above 0.95 and a load balancing index of approximately 0.95 during non-stationary transitions. A longitudinal self-degradation analysis further shows that SCFL preserves historical knowledge with near-zero performance variation in spatial reliability and QoS under moderate loads from 40 to 120 users, while revealing its operating boundary under extreme congestion with 140 users due to hard projection constraints. The framework provides a scalable, communication-efficient approach for autonomous aerial network orchestration.