Score: 3

Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning

Published: January 6, 2026 | arXiv ID: 2601.02972v1

By: Nathanaël Carraz Rakotonirina , Ren Pang , Neha Anna John and more

BigTech Affiliations: Amazon

Potential Business Impact:

Makes AI think less to solve problems faster.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes unnecessarily long, increasing computation cost without actual accuracy gains or sometimes even degrading performance, a phenomenon known as ``overthinking''. We propose a multi-stage efficient reasoning method that combines supervised fine-tuning -- via rejection sampling or reasoning trace reformatting -- with reinforcement learning using an adaptive length penalty. We introduce a lightweight reward function that penalizes tokens generated after the first correct answer but encouraging self-verification only when beneficial. We conduct a holistic evaluation across seven diverse reasoning tasks, analyzing the accuracy-response length trade-off. Our approach reduces response length by an average of 28\% for 8B models and 40\% for 32B models, while incurring only minor performance drops of 1.6 and 2.5 points, respectively. Despite its conceptual simplicity, it achieves a superior trade-off compared to more complex state-of-the-art efficient reasoning methods, scoring 76.6, in terms of the area under the Overthinking-Adjusted Accuracy curve ($\text{AUC}_{\text{OAA}}$) -- 5 points above the base model and 2.5 points above the second-best approach.

Country of Origin
🇪🇸 🇺🇸 Spain, United States

Page Count
13 pages

Category
Computer Science:
Computation and Language