Metraipolis › archive › dc_e81d0dc79cb0

Capture the lifecycle: KV Cache management in ReAct Agents with KVTether — arXiv:2609.39819

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39819
License (as archived)
CC0-1.0
Archived
2026-10-07T15:20:09.693Z
SHA-256 of the archived text
08664cf3f559abe4a0acd2174bb20b524ef43e6c26f1f50bcf384af4a0f107d0
Stable URL of this page
https://metraipolis.com/documento/dc_e81d0dc79cb0

How to cite

Capture the lifecycle: KV Cache management in ReAct Agents with KVTether — arXiv:2609.39819 — arXiv (en), https://arxiv.org/abs/2609.39819 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e81d0dc79cb0 (Metraipolis archive dc_e81d0dc79cb0, sha256 08664cf3f559abe4a0acd2174bb20b524ef43e6c26f1f50bcf384af4a0f107d0)
BibTeX
@misc{dce81d0dc79cb0,
  title = {Capture the lifecycle: KV Cache management in ReAct Agents with KVTether — arXiv:2609.39819},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39819},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e81d0dc79cb0; sha256 08664cf3f559abe4a0acd2174bb20b524ef43e6c26f1f50bcf384af4a0f107d0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39819. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Efficient serving of long-context reasoning-and-acting (ReAct) agents relies on KV cache reuse to reduce large language model (LLM) prefill latency and monetary cost. However, a semantic gap exists between agent harnesses and the underlying serving stack. Through context mutation, tool execution, and subagent coordination, context messages may become actively engaged, permanently discarded, and temporarily unused, while the serving stack only observes accesses to the corresponding KV cache. This lifecycle blindness prevents recency-only policies such as LRU from reclaiming dead KV promptly and from preserving older KV that will be reused sooner than newer entries. We present KVTether, a lifecycle-aware KV cache management framework for ReAct agents. By tracing semantic primitives embedded in agent harnesses, KVTether captures runtime lifecycle semantics during highly dynamic execution. KVTether then translates message-level semantics into KV-level lifecycle states and uses these states to drive state-prioritized cache management without exposing physical complexities to agent harnesses. After reclaiming dead KV, KVTether preferentially preserves live-but-idle KV that is waiting for reuse, reducing premature eviction before reuse. Across agent benchmarks and production workloads, KVTether reduces end-to-end request latency by up to 26.3% and 17.4% relative to LMCache and MORI, respectively, and lowers estimated task cost by 40.0% and 33.2% on average.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-10-01 in cs.OS).
Categorie arXiv: Operating Systems (cs.OS).
Pagina del lavoro: https://arxiv.org/abs/2609.39819 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T14:53:17.072Z dalla pagina https://arxiv.org/catchup/cs.OS/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).