Metraipolis › archive › dc_f03b4ea34abc

SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking — arXiv:2611.07558

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07558
License (as archived): CC0-1.0
Archived: 2026-11-06T14:42:27.196Z
SHA-256 of the archived text: f7e1301803062b1e0410149898ecf5818e92603159a2b1fe73e81d709ac442d4
Stable URL of this page: https://metraipolis.com/documento/dc_f03b4ea34abc

How to cite

SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking — arXiv:2611.07558 — arXiv (en), https://arxiv.org/abs/2611.07558 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f03b4ea34abc (Metraipolis archive dc_f03b4ea34abc, sha256 f7e1301803062b1e0410149898ecf5818e92603159a2b1fe73e81d709ac442d4)

BibTeX

@misc{dcf03b4ea34abc,
  title = {SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking — arXiv:2611.07558},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07558},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f03b4ea34abc; sha256 f7e1301803062b1e0410149898ecf5818e92603159a2b1fe73e81d709ac442d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07558. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Model (LLM) agents are increasingly deployed under structured generation, where grammar constraints enforce output format at inference time. Whereas existing compression methods target unconstrained generation, we first identify a fundamental mismatch: under structured generation, grammar constraints reduce the model's output distribution to valid tokens, and the logits matter most at the small set of positions that decide the agent's action. Motivated by this finding, we propose SKIM (Selective Knowledge-Informed Masking), the first pruning and distillation framework for LLM agents under structured generation, with both stages guided by token role. SKIM partitions token positions into context, decision, and format categories, and this partition drives two complementary axes: (1) category-aware pruning saliency scores that preserve parameters most relevant for decision positions; and (2) an on-policy distillation objective that aligns student and teacher on valid tokens, paired with category-aware feature matching. We evaluate SKIM on tool-calling benchmarks and within multi-step agent loops, across multiple model scales and sparsity levels. SKIM consistently improves accuracy over baselines, with its superiority becoming most striking in high-sparsity regimes where conventional methods struggle, demonstrating the potential of category-aware compression for deployment-time grammar-constrained agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.07558 — 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 2026-11-06T14:18:42.679Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).