发表机构
Shanghai Jiao Tong University, Computer Institute; Shanghai Landfun Information Technology（上海交通大学计算机学院; 上海蓝帆信息技术有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对离线资源受限边缘设备上SLMs多步任务可靠性差的问题，提出PTC-Decoder，通过计划原子化与令牌级硬约束，在无需训练下提升步骤级可靠性，平均得分提升+1.21。
AI 中文摘要
在离线、资源受限的边缘设备（如遥感卫星）上部署小型语言模型（SLMs）面临一个根本性挑战：其有限的推理能力阻碍了需要复杂工具编排的多步智能体任务的可靠执行。现有的计划-解决范式依赖于基于提示的强制，而我们的实验表明SLMs几乎完全忽视这种强制：弱模型无法调用计划。我们提出PTC-Decoder（计划-工具约束解码器），一种无需训练、即插即用的解码器框架，它结合了（1）计划到行动范式，将计划提升为原子工具并强制其在推理第一步被调用，以及（2）TC-Decoder，一种确定性有限自动机，对工具名称施加令牌级硬约束，同时保留参数生成的自由度，从而保持SLM的推理能力。在7个SLM上对200个真实遥感卫星任务进行评估，PTC-Decoder实现了统计显著的总体平均得分提升+1.21（p<0.01），95%置信区间[+1.13, +1.29]），并在不同模型和其他数据集上保持一致改进。一项去除TC-Decoder的消融研究在所有质量指标上导致显著性能下降，且未降低计算成本，确认TC-Decoder是主要驱动因素。因此，PTC-Decoder提供了一种轻量级但有效的解决方案，用于提高步骤级可靠性，而最终答案准确性仍是一个开放挑战。本质上，我们通过在推理期间约束允许的输出词汇来强制计划遵循，无需重新训练。
英文摘要
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.
