Cover Image

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Si, Wenwen, Lee, Insup, Bastani, Osbert
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Conformal Constrained Policy Optimization for Cost-Effective LLM Agents
by: Si, Wenwen, et al.
Published: (2025)

Effective Reinforcement Learning for Reasoning in Language Models
by: Huang, Lianghuan, et al.
Published: (2025)

TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction
by: Li, Shuo, et al.
Published: (2023)

Are AI Capabilities Increasing Exponentially? A Competing Hypothesis
by: Ge, Haosen, et al.
Published: (2026)

Uncertainty in Language Models: Assessment through Rank-Calibration
by: Huang, Xinmeng, et al.
Published: (2024)

Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
by: Yao, Michael S., et al.
Published: (2025)

Decaf: Improving Neural Decompilation with Automatic Feedback and Search
by: Shypula, Alexander, et al.
Published: (2026)

Generative Adversarial Model-Based Optimization via Source Critic Regularization
by: Yao, Michael S., et al.
Published: (2024)

Rubric-Guided Process Reward for Stepwise Model Routing
by: Ye, Shenghao, et al.
Published: (2026)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
by: Chen, Peter, et al.
Published: (2025)

Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine
by: Yao, Michael S., et al.
Published: (2025)

DrEureka: Language Model Guided Sim-To-Real Transfer
by: Ma, Yecheng Jason, et al.
Published: (2024)

RAPID: An Efficient Reinforcement Learning Algorithm for Small Language Models
by: Huang, Lianghuan, et al.
Published: (2025)

BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
by: Anupam, Sagnik, et al.
Published: (2025)

Evaluating the Diversity and Quality of LLM Generated Content
by: Shypula, Alexander, et al.
Published: (2025)

Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning
by: Luo, Yihong, et al.
Published: (2025)

PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications
by: Mell, Stephen, et al.
Published: (2026)

Eurekaverse: Environment Curriculum Generation via Large Language Models
by: Liang, William, et al.
Published: (2024)

One-Shot Safety Alignment for Large Language Models via Optimal Dualization
by: Huang, Xinmeng, et al.
Published: (2024)

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
by: Lee, Sangmook, et al.
Published: (2025)

RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
by: Sridhar, Kaustubh, et al.
Published: (2025)

TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks
by: Kapoor, Vansh, et al.
Published: (2026)

Asymptotic Normality of Generalized Low-Rank Matrix Sensing via Riemannian Geometry
by: Bastani, Osbert
Published: (2024)

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
by: Cui, Yingqian, et al.
Published: (2025)

Stepwise Reasoning Error Disruption Attack of LLMs
by: Peng, Jingyu, et al.
Published: (2024)

Promoting Efficient Reasoning with Verifiable Stepwise Reward
by: Yue, Chuhuai, et al.
Published: (2025)

RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning
by: Tian, Jiayi, et al.
Published: (2026)

REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments
by: Sridhar, Kaustubh, et al.
Published: (2024)

Pattern-Guided Diffusion Models
by: Lin, Vivian, et al.
Published: (2025)

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models
by: Yu, Song, et al.
Published: (2026)

Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment
by: Zhang, Lijun, et al.
Published: (2025)

InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward
by: Ning, Zhiwei, et al.
Published: (2026)

Beating the Winner's Curse via Inference-Aware Policy Optimization
by: Bastani, Hamsa, et al.
Published: (2025)

TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models
by: Imani, Shima, et al.
Published: (2025)

Stepwise Alignment for Constrained Language Model Policy Optimization
by: Wachi, Akifumi, et al.
Published: (2024)

Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning
by: Hu, Pengfei, et al.
Published: (2024)

Tether: Autonomous Functional Play with Correspondence-Driven Trajectory Warping
by: Liang, William, et al.
Published: (2026)

Eureka: Human-Level Reward Design via Coding Large Language Models
by: Ma, Yecheng Jason, et al.
Published: (2023)

Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
by: Zhao, Zilong, et al.
Published: (2024)

Latent Veracity Inference for Identifying Errors in Stepwise Reasoning
by: Kim, Minsu, et al.
Published: (2025)