Metraipolis › archive › dc_75df4869d586
PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices — arXiv:2609.30836
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30836
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:38:22.293Z
- SHA-256 of the archived text
723497d7eddbb568946b952e7ffdcb06db2707f51e5a5f1091866ddd47ec8455- Stable URL of this page
https://metraipolis.com/documento/dc_75df4869d586
How to cite
PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices — arXiv:2609.30836 — arXiv (en), https://arxiv.org/abs/2609.30836 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75df4869d586 (Metraipolis archive dc_75df4869d586, sha256 723497d7eddbb568946b952e7ffdcb06db2707f51e5a5f1091866ddd47ec8455)
BibTeX
@misc{dc75df4869d586,
title = {PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices — arXiv:2609.30836},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30836},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75df4869d586; sha256 723497d7eddbb568946b952e7ffdcb06db2707f51e5a5f1091866ddd47ec8455},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30836. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deploying small language models (SLMs) on offline, resource-constrained edge devices such as remote sensing satellites presents a fundamental challenge: their limited reasoning capacity hinders reliable execution of multi-step agent tasks requiring complex tool orchestration. Existing plan-solve paradigms rely on prompt-based enforcement, which our experiments show SLMs almost entirely disregard: weak models fail to invoke the plan. We propose PTC-Decoder (Plan-Tool Constrained Decoder), a training-free, plug-and-play decoder framework that combines (1) a Plan-to-Act paradigm, which elevates planning to an atomic tool and forces its invocation at the first inference step, and (2) TC-Decoder, a deterministic finite automaton that imposes token-level hard constraints on tool names while preserving freedom over parameter generation, thereby retaining SLM reasoning capability. Evaluated on 200 real remote-sensing satellite tasks across 7 SLMs, PTC-Decoder yields a statistically significant mean overall score gain of +1.21 (p<0.01), 95% CI [+1.13, +1.29]), with consistent improvements across models and other datasets. An ablation study that removes TC-Decoder causes substantial performance degradation across all quality metrics without reducing computational cost, confirming TC-Decoder as the primary driver. PTC-Decoder thus offers a lightweight yet effective solution for improving step-level reliability, with final-answer accuracy remaining an open challenge. In essence, we enforce plan adherence by constraining the permissible output vocabulary during inference, without requiring retraining. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.30836 — 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 2026-10-08T01:12:14.294Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).