paper-with-me

Papers

Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective

2026-05-28 · Shenghao Ye, Yuxiang Wang, Yu Guo, Dong Jin, Shuangwu Chen, Jian Yang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.29319

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Rubric-Guided Process Reward for Stepwise Model Routing

2026-05-28 · Shenghao Ye, Yu Guo, Zhengheng Li, Shuangwu Chen 외 arxiv

Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router…

Reinforcement Learning

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning

2026-05-07 · Wenwen Si, Insup Lee, Osbert Bastani arxiv

Inference-time computation has greatly enhanced the performance of large language models (LLMs) on challenging reasoning tasks, but this strategy can incur high inference costs. One solution is to route intermediate chai…

Reinforcement Learning

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning

2025-11-09 · Sangmook Lee, Dohyung Kim, Hyukhun Koh, Nakyeong Yang 외 arxiv

Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To low…

Mathematical Reasoning

TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks

2026-01-15 · Vansh Kapoor, Aman Gupta, Hao Chen, Anurag Beniwal 외 arxiv

Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to complete solution breakdown. Current LLM routing methods assign entire queries to …

From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing

2026-06-05 · Guannan Lai, Haoran Hu, Long Chen, Zhenguo Li 외 arxiv

Existing LLM routing methods often construct supervision from a single sampled response for each query--model pair. Because LLM generation is stochastic, however, such an observation can be an unstable estimate of model …