# SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling

arXiv: https://arxiv.org/abs/2607.08565 · HTML: https://mlsanity.com/paper/2607.08565/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 50 of its 80 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 50)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion](https://mlsanity.com/paper/2405.16444/) (2024)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention](https://mlsanity.com/paper/2403.19708/) (2024)
- [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://mlsanity.com/paper/2006.02464/) (2020)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [Parrot: Efficient Serving of LLM-based Applications with Semantic Variable](https://mlsanity.com/paper/2405.19888/) (2024)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [NanoFlow: Towards Optimal Large Language Model Serving Throughput](https://mlsanity.com/paper/2408.12757/) (2024)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition](https://mlsanity.com/paper/2402.15220/) (2024)
- [Fairness in Serving Large Language Models](https://mlsanity.com/paper/2401.00588/) (2023)
- [Preble: Efficient Distributed Prompt Scheduling for LLM Serving](https://mlsanity.com/paper/2407.00023/) (2024)
- [Stateful Large Language Model Serving with Pensieve](https://mlsanity.com/paper/2312.05516/) (2023)
- [Autellix: An Efficient Serving Engine for LLM Agents as General Programs](https://mlsanity.com/paper/2502.13965/) (2025)
- [Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow](https://mlsanity.com/paper/2406.01566/) (2024)
- [POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference](https://mlsanity.com/paper/2410.18038/) (2024)
- [Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services](https://mlsanity.com/paper/2404.16283/) (2024)
- [KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider](https://mlsanity.com/paper/2506.02634/) (2025)

## Built on by (most cited first, 2 of 2)

- [When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse](https://mlsanity.com/paper/2609.28870/) (2026)
- [LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound](https://mlsanity.com/paper/2609.32256/) (2026)

## Abstract (arXiv)

LLM scheduling is critical to serving, yet how well existing designs fit agentic serving--where agents, not humans, issue the requests--remains unclear. Agents shift the workload in two ways: they consume many more tokens than humans, so the cluster must provide high throughput (TPS) at low latency; and their requests reuse far more KV than chat. Existing schedulers still trade off load balance against KV reuse: cache-aware schedulers may crowd requests onto the few instances caching the KV, leaving the rest idle, while balanced schedulers may lose the opportunity for reuse, which is costly at a high reuse ratio. We thus present two key insights: (1) with a global-tier KV store, pursuing load balance need not compromise KV reuse, though the slower global tier must be used with care; and (2) given the agent's intra-session locality, routing requests by their sessions can balance the load with high KV reuse. A key challenge in realizing session-centric scheduling is that the scheduler must identify a request's session statelessly, which is difficult for model providers serving arbitrary agents. SMetric addresses this with differential scheduling based on two indicators derived from the request itself, the session turn and the local KV hit: it schedules first-turn requests for load balance, and sticks follow-ups to the instance with the highest local hit for high KV reuse. As sessions differ widely in size, SMetric sticks a follow-up only if the instance can serve it within its SLO, and otherwise migrates the session to the least-loaded instance to prevent many long sessions from eventually imbalancing the load. Evaluated on real-world traces, SMetric improves the peak TPS by 9-15% under prefill-decode colocation with a provisioned global tier and the peak prefill TPS by 9% under disaggregation over state-of-the-art schedulers, also with lower latency.