Paper Detail

Evolving Infra: Agent-Adaptive LLM Serving at Scale

Hao Kang, Weili Xu, Ziyang Li, Zheng Du, Hanchen Li, Tian Xia, Song Bian, Tushar Krishna, Huizi Mao, Ion Stoica, Song Han

huggingface Score 6.4

Published 2026-11-09 · First seen 2026-11-12

General AI

Abstract

Agentic workloads are a major source of LLM inference demand. Existing prefill--decode (PD) disaggregated serving systems offer limited flexibility for runtime adaptation of compute allocation and KV cache management, and rely on coarse signals that only partly capture the diverse and dynamic agent workload. These limitations lead to load imbalance between prefill and decode nodes and eviction of KV caches that agents will reuse. We present Evolving Infra, an agent-adaptive serving framework that adapts compute allocation to agent workloads and KV cache management to agent context management at runtime. We decouple compute allocation from key--value (KV) cache management, allowing nodes to switch efficiently between prefill and decode. Building on this design, an online planner matches the PD split to workload composition, while an agent-aware distributed KV manager guides cache eviction and transfer with signals from agent context management. Across coding, math, and computer-use tasks with GLM-5.2 and Kimi K2.6 on up to 256 GB300 GPUs, Evolving Infra reduces mean end-to-end request latency and P95 TTFT by up to 4.1x and 14x over Dynamo, NVIDIA's production framework.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{kang2026evolving,
  title = {Evolving Infra: Agent-Adaptive LLM Serving at Scale},
  author = {Hao Kang and Weili Xu and Ziyang Li and Zheng Du and Hanchen Li and Tian Xia and Song Bian and Tushar Krishna and Huizi Mao and Ion Stoica and Song Han},
  year = {2026},
  abstract = {Agentic workloads are a major source of LLM inference demand. Existing prefill--decode (PD) disaggregated serving systems offer limited flexibility for runtime adaptation of compute allocation and KV cache management, and rely on coarse signals that only partly capture the diverse and dynamic agent workload. These limitations lead to load imbalance between prefill and decode nodes and eviction of KV caches that agents will reuse. We present Evolving Infra, an agent-adaptive serving framework tha},
  url = {https://huggingface.co/papers/2611.12304},
  keywords = {code available, huggingface daily},
  eprint = {2611.12304},
  archiveprefix = {arXiv},
}

Metadata

{}