arXiv:2607. 16891v1 Announce Type: cross Abstract: A truckload carrier must accept or reject each load tender within seconds.
By Aswin Chandrasekaran
The paper argues that large language model (LLM) providers, constrained by compute, often degrade service during congestion by routing queries to smaller models, cutting reasoning effort, or truncating context. It shows that this practice misrepresents costs because degraded answers can fail, leading to retries that inflate traffic or churn that erodes lifetime value. By modeling inference allocation with newsvendor, retry, and queueing frameworks, the authors derive a ‘shadow price of intelligence’ that quantifies the marginal value of each query, revealing that throttling under congestion acts as a demand lever rather than a cost lever.
By Elioth Sanabria
arXiv:2606. 10472v1 Announce Type: cross Abstract: Dynamic multi-resource allocation is a central problem in shared computing environments, where users' demands arrive sequentially and resources must be distributed fairly without knowledge of future demands.
By Kaiqi Jiang, Karim El Husseini, Wenzhe Fan, Xinhua Zhang
The paper proposes a method for routing requests to a fixed pool of quantized Mixture-of-Experts (MoE) instances, aiming to maximize throughput while respecting a quality‑degradation budget. It introduces Fragility‑Weighted Perplexity (FWP) as a request‑specific risk metric derived from prompt tokens, and uses a window‑level linear program to compute a reduced‑reward score that aligns with the LP optimum. Experiments on Qwen prompts show that FWP‑based allocation improves throughput by 2.5% over request‑agnostic mixing and static configurations.
By Zhenghong Huang, Hongfan Wu, Jiheng Zhang
arXiv:2607. 26788v1 Announce Type: cross Abstract: Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such clustering is sustainable only if participants prefer their assigned coalition and the required transfers are affordable.
By Cengis Hasan
arXiv:2607. 08565v1 Announce Type: cross Abstract: LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans.
By Jiahao Wang, Kaizhan Lin, Kaixi Zhang, Jinbo Han, Xingda Wei, Sijie Shen, Chenguang Fang, Wenyuan Yu, Rong Chen, Haibo Chen