The field of serverless computing and cloud marketspaces is witnessing significant advancements, driven by the need for efficient and cost-effective resource management. Researchers are focusing on developing innovative simulation tools and frameworks to analyze and optimize the performance of serverless platforms. These tools enable the simulation of complex behaviors, such as request routing, cold starts, and function scaling, allowing for a deeper understanding of the underlying mechanics. Additionally, there is a growing interest in modeling and evaluating dynamic cloud marketspaces, including spot instance behavior and scheduling. This has led to the development of new simulation frameworks and allocation algorithms that can efficiently manage resources in volatile workload environments. Furthermore, researchers are exploring ways to reduce latency in search agents and improve the serving of agentic workflows, leading to breakthroughs in speculation-based algorithm-system co-design and just-in-time model routing. Noteworthy papers include:

• Serv-Drishti, which presents an interactive serverless function request simulation engine and visualiser,
• Simulating Dynamic Cloud Marketspaces, which extends the CloudSim Plus simulation framework to support realistic spot instance lifecycle management,
• Reducing Latency of LLM Search Agent, which introduces a speculation-based algorithm-system co-design framework to reduce latency,
• Aragog, which presents a system for just-in-time model routing for scalable serving of agentic workflows.