根据任务进展动态切换大模型，省钱又提成功率。
TACIT-Switch: Cost-Aware Model Escalation for LLM Agents from Censored Supervision
- 用累积风险与截尾标注训练永久切换策略
- 在ALFWorld和DABench上成功率达48.5%~73.1%
- 无需部署时教师，适合资源受限的长任务代理
小型语言模型成本低但易陷入持续失败，大型模型更可靠但开销大。本文提出TACIT-SWITCH方法，通过学习累积轨迹证据与教师标注的截尾干预时间（TACIT）来确定何时切换至大模型。将每条标注视为累积风险尺度上的区间截尾观测，构建混合治愈阈值模型，估计强模型成功概率及切换阈值，部署时无需教师。在机制驱动的多步仿真中，相较任务级、步骤级和固定前缀基线，在相近成本下成功率提升7.4-11.1个百分点。消融实验表明任务特征与累积轨迹风险信息互补。在开发数据上选择运行点后，TACIT-SWITCH在ALFWorld（4B Cheap：48.5%；9B Cheap：45.5%）和DABench（73.1%）上均达到最优保留成功率。
原文摘要 · Abstract (English)
Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are generally more reliable but more costly. This reliability-cost trade-off motivates routing methods that decide when to invoke an agent with a larger backbone: before execution, after a fixed trajectory prefix, or locally at individual steps. Our method, TACIT-SWITCH, learns permanent handoff policies from accumulated trajectory evidence and Teacher-Annotated Censored Intervention Times (TACIT). It represents each annotation as an interval-censored observation on a cumulative-risk scale. The resulting mixture-cure threshold model estimates the probability that the paired Strong rollout succeeds and, conditional on success, the handoff threshold; no teacher is required at deployment. In a mechanism-based multi-step simulation, TACIT-SWITCH improves success by 7.4-11.1 percentage points over task-level, step-level, and fixed-prefix routing baselines at comparable cost. Within that controlled simulation, ablations show that task features and cumulative trajectory risk provide complementary information. With operating points selected on development data, TACIT-SWITCH achieves the highest held-out success among learned policies on both ALFWorld (48.5% with 4B Cheap; 45.5% with 9B Cheap) and DABench (73.1%).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。