用表格文本分类器替代大模型决策，显著降低智能体运行延迟和成本。
TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifiers
- 从执行轨迹中提取结构化特征，构建小型分类器替代生成式决策模块。
- 在长程任务上保持成功率，延迟降低95%，推理成本减少85%-91%。
- 适用于路由、筛选等场景，适合生产环境中的智能体优化。
智能体系统常通过多次调用大语言模型完成封闭集决策任务（如路由、短列、过滤、验证），但导致部署延迟高、成本大。本文提出TabAgent框架，将生成式决策组件替换为基于执行轨迹训练的轻量级文本-表格分类器。该框架（i）从轨迹中提取结构化模式、状态与依赖特征（TabSchema）；（ii）通过对齐模式的合成数据增强覆盖（TabSynth）；（iii）使用轻量分类器（TabHead）打分候选。在长周期的AppWorld基准测试中，TabAgent维持任务成功率，同时消除短列阶段的LLM调用，使延迟降低约95%，推理成本下降85%-91%。该方法可推广至其他决策模块，为生产级智能体架构中生成瓶颈的判别式替代提供新范式。
原文摘要 · Abstract (English)
Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as routing, shortlisting, gating, and verification. While convenient, this design makes deployments slow and expensive due to cumulative latency and token usage. We propose TabAgent, a framework for replacing generative decision components in closed-set selection tasks with a compact textual-tabular classifier trained on execution traces. TabAgent (i) extracts structured schema, state, and dependency features from trajectories (TabSchema), (ii) augments coverage with schema-aligned synthetic supervision (TabSynth), and (iii) scores candidates with a lightweight classifier (TabHead). On the long-horizon AppWorld benchmark, TabAgent maintains task-level success while eliminating shortlist-time LLM calls, reducing latency by approximately 95% and inference cost by 85-91%. Beyond tool shortlisting, TabAgent generalizes to other agentic decision heads, establishing a paradigm for learned discriminative replacements of generative bottlenecks in production agent architectures.
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。