Metraipolis › archive › dc_6b05ee7769db
ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents — arXiv:2608.19662
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19662
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T11:39:12.624Z
- SHA-256 of the archived text
86542dfe47ba172eed2e30aafab603df1a9401cda644b32384598a25d88972de- Stable URL of this page
https://metraipolis.com/documento/dc_6b05ee7769db
How to cite
ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents — arXiv:2608.19662 — arXiv (en), https://arxiv.org/abs/2608.19662 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b05ee7769db (Metraipolis archive dc_6b05ee7769db, sha256 86542dfe47ba172eed2e30aafab603df1a9401cda644b32384598a25d88972de)
BibTeX
@misc{dc6b05ee7769db,
title = {ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents — arXiv:2608.19662},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19662},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b05ee7769db; sha256 86542dfe47ba172eed2e30aafab603df1a9401cda644b32384598a25d88972de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19662. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states. We introduce \textbf{ReCache}, a framework for independently caching resource representations while reducing their inference-time computational and memory overhead. Resource-wise attention removes cross-resource interactions and assigns resource-local positions, producing composition-invariant KV blocks. ReCache then restricts resource visibility to contribution-selected layer--KV-head-group routes and retains only invocation-critical fields through structural and semantic pruning. We evaluate ReCache on a benchmark assembled from seven public tool- and skill-use datasets, including resource-disjoint tests. Resource-wise attention matches dense invocation performance (82.3\% versus 82.4\% Inv-F1) while providing a 3.655$\times$ time-to-first-token speedup. The complete framework reduces allocated KV-tensor memory by 92.43\% and accelerates attention by 1.423$\times$. These results show that separating reusable schema encoding from selective resource access substantially reduces agentic inference costs with limited effectiveness loss. The code is available at this https URL .
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.19662 — 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 2026-10-18T11:38:27.902Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).