arXiv cs.CL· Shenghao Ye, Yuxiang Wang, Yu Guo, Tao Zhang, Shuangwu Chen, Zijian Wen, Qihui Zhu, Mengjie Zhang, Dong Jin, Wang Luo, Jian Yang·· 11 小时前AI 评分22
EcoTab：面向表格推理的表格感知逐步模型路由框架
Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective
AI 导读
针对大推理模型（LRM）在表格推理中推理成本高的问题，研究者提出 EcoTab——一个表格感知的逐步路由框架，分别估计表格 token 与文本 token 的不确定性并映射为小模型下一步失败风险，再融合两类风险做路由决策。在多个表格推理基准上，EcoTab 稳定优于强基线，在准确率与效率之间取得更好平衡。该工作已被 EMNLP 2026 主会接收。
正文 · 原文
Authors:Shenghao Ye, Yuxiang Wang, Yu Guo, Tao Zhang, Shuangwu Chen, Zijian Wen, Qihui Zhu, Mengjie Zhang, Dong Jin, Wang Luo, Jian Yang
Abstract:Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Stepwise model routing mitigates this issue by dynamically assigning reasoning steps to smaller or larger models. However, stepwise model routing for table reasoning remains underexplored. Through empirical analysis, we find that reasoning steps involving tables contain two types of tokens with distinct uncertainty distributions: table tokens grounded in table structure, such as cell values and headers, and text tokens representing surrounding natural-language reasoning. The uncertainty of both token types is correlated with the risk that the model makes an error in the next reasoning step. However, existing methods fail to model them separately, leading to suboptimal routing decisions. To address this, we propose EcoTab, a table-aware stepwise routing framework for efficient table reasoning. At each reasoning step, EcoTab separately estimates the uncertainties of table tokens and text tokens, maps them to next-step failure risks for the small model, and combines the two risks for routing. Experiments on multiple table reasoning benchmarks show that EcoTab consistently outperforms strong baselines and achieves a better balance between accuracy and efficiency.
| Comments: | 17pages, 15 figures, accepted to EMNLP 2026 Main |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.29319 [cs.CL] |
| (or arXiv:2605.29319v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.29319 arXiv-issued DOI via DataCite |
Submission history
From: Ye Shenghao [view email]
[v1]
Thu, 28 May 2026 03:49:10 UTC (1,842 KB)
[v2]
Mon, 2 Nov 2026 04:10:13 UTC (1,850 KB)
来源：arXiv cs.CL · arxiv.org