# CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents

arXiv: https://arxiv.org/abs/2606.16824 · HTML: https://mlsanity.com/paper/2606.16824/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Efficient reasoning and agent inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- Efficient LLM inference and serving / [Efficient reasoning and agent inference](https://mlsanity.com/inference/efficient-reasoning-and-agent-inference/)

## Builds on (most cited first, 26 of 26)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (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)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management](https://mlsanity.com/paper/2406.19707/) (2024)
- [Competitive caching with machine learned advice](https://mlsanity.com/paper/1802.05399/) (2018)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments](https://mlsanity.com/paper/2510.01179/) (2025)
- [Autellix: An Efficient Serving Engine for LLM Agents as General Programs](https://mlsanity.com/paper/2502.13965/) (2025)
- [NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference](https://mlsanity.com/paper/2411.01142/) (2024)
- [Jenga: Effective Memory Management for Serving LLM with Heterogeneity](https://mlsanity.com/paper/2503.18292/) (2025)
- [PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications](https://mlsanity.com/paper/2505.07203/) (2025)
- [T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning](https://mlsanity.com/paper/2505.16986/) (2025)
- [Pie: A Programmable Serving System for Emerging LLM Applications](https://mlsanity.com/paper/2510.24051/) (2025)
- [EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving](https://mlsanity.com/paper/2512.14946/) (2025)
- [LLM Query Scheduling with Prefix Reuse and Latency Constraints](https://mlsanity.com/paper/2502.04677/) (2025)

## Built on by (most cited first, 10 of 10)

- [TokTier: Exact Stateful CPU+GPU Tokenization for Agentic LLM Serving](https://mlsanity.com/paper/2607.29678/) (2026)
- [Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving](https://mlsanity.com/paper/2609.27085/) (2026)
- [Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection](https://mlsanity.com/paper/2607.05148/) (2026)
- [Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management](https://mlsanity.com/paper/2609.06940/) (2026)
- [Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It](https://mlsanity.com/paper/2609.18849/) (2026)
- [The KV Cache Working Set: Online Capacity Planning for LLM Inference Systems](https://mlsanity.com/paper/2609.27746/) (2026)
- [When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse](https://mlsanity.com/paper/2609.28870/) (2026)
- [AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines](https://mlsanity.com/paper/2610.01108/) (2026)
- [Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.16592/) (2026)
- [Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs](https://mlsanity.com/paper/2610.19801/) (2026)

## Abstract (arXiv)

Coding agents are a fast-growing LLM application, executing as long-running closed-loop sessions in which LLM generations alternate with external tool calls. Yet, unlike chat workloads, their serving behavior has not been studied extensively. We address this gap by collecting a dataset of real-world coding assistant traces. Our analysis shows that coding agent sessions repeatedly reuse large prefixes and create sustained KVCache pressure that conventional LLM serving policies handle poorly. Based on our analysis, we present CacheWise, a KVCache management layer that improves KVCache reuse for coding agent workloads. CacheWise combines prefix-aware scheduling with reuse-aware eviction guided by lightweight predictions from tool call metadata. Implemented in vLLM and evaluated on the collected traces, CacheWise reduces KVCache evictions by up to 2-2.6x and improves total agent session completion time by up to 3.5x.