Metraipolis › archive › dc_9d92b9afdeff

SpecCompact: Accelerating LLM Agent Context Compaction with Slot-Parallel Semantic Speculative Verification — arXiv:2611.06876

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06876
License (as archived)
CC0-1.0
Archived
2026-11-05T18:18:54.507Z
SHA-256 of the archived text
58f063d211f0779ebbef06746170abfc42b4f3cc4017c58b2115b7ff12118aae
Stable URL of this page
https://metraipolis.com/documento/dc_9d92b9afdeff

How to cite

SpecCompact: Accelerating LLM Agent Context Compaction with Slot-Parallel Semantic Speculative Verification — arXiv:2611.06876 — arXiv (en), https://arxiv.org/abs/2611.06876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9d92b9afdeff (Metraipolis archive dc_9d92b9afdeff, sha256 58f063d211f0779ebbef06746170abfc42b4f3cc4017c58b2115b7ff12118aae)
BibTeX
@misc{dc9d92b9afdeff,
  title = {SpecCompact: Accelerating LLM Agent Context Compaction with Slot-Parallel Semantic Speculative Verification — arXiv:2611.06876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9d92b9afdeff; sha256 58f063d211f0779ebbef06746170abfc42b4f3cc4017c58b2115b7ff12118aae},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents use context compaction to manage growing interaction histories, but summarizing long histories with large models can introduce substantial delays. Compaction therefore requires balancing information retention against latency. We observe that structured summary slots can retain information when generated independently. Based on this observation, we present SpecCompact, a framework that accelerates compaction through slot-parallel semantic speculation. SpecCompact fine-tunes a small drafter and generates slots in parallel. The target model verifies each proposed line and repairs rejected content, while subsequent drafting uses the updated slot prefix. System optimizations further reduce repeated context processing and model calls. Across AppWorld and $\tau^3$ benchmarks with two target models, SpecCompact achieves $2.04$--$5.63\times$ compaction speedups over Hermes-style summarization. Separate downstream evaluations reveal model- and task-dependent performance trade-offs. A user study within Hermes further shows an $8.68\times$ median compaction speedup.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.06876 — 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 2026-11-05T18:13:03.951Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).