The field of multi-agent pathfinding and temporal graph reconfiguration is experiencing significant growth, with a focus on developing efficient and effective algorithms for complex scenarios. Recent research has explored the use of hybrid frameworks, combining learned heuristics with search-based algorithms, to improve solution quality in dense multi-agent pathfinding problems. Additionally, there is a growing interest in providing local guidance to agents, rather than relying on global guidance, to mitigate congestion and improve overall coordination efficiency. Noteworthy papers in this area include: Temporal Graph Reconfiguration for Always-Connected Graphs, which introduces the temporal graph reconfiguration problem and provides a polynomial-time algorithm for solving it. Graph Attention-Guided Search for Dense Multi-Agent Pathfinding, which develops a hybrid framework that integrates a learned heuristic with a search-based algorithm to achieve state-of-the-art results in dense multi-agent pathfinding scenarios.