Control-R: Towards controllable test-time scaling
It addresses controllable reasoning for complex tasks in AI, though it appears incremental as it builds on existing chain-of-thought methods.
This paper tackles the problem of underthinking and overthinking in long chain-of-thought reasoning for Large Reasoning Models by introducing Reasoning Control Fields, a test-time approach that guides reasoning with control signals, achieving state-of-the-art performance on benchmarks like AIME2024 and MATH500 at the 32B scale.
This paper target in addressing the challenges of underthinking and overthinking in long chain-of-thought (CoT) reasoning for Large Reasoning Models (LRMs) by introducing Reasoning Control Fields (RCF)--a novel test-time approach that injects structured control signals to guide reasoning from a tree search perspective. RCF enables models to adjust reasoning effort according to given control conditions when solving complex tasks. Additionally, we present the Control-R-4K dataset, which consists of challenging problems annotated with detailed reasoning processes and corresponding control fields. To further enhance reasoning control, we propose a Conditional Distillation Finetuning (CDF) method, which trains model--particularly Control-R-32B--to effectively adjust reasoning effort during test time. Experimental results on benchmarks such as AIME2024 and MATH500 demonstrate that our approach achieves state-of-the-art performance at the 32B scale while enabling a controllable Long CoT reasoning process (L-CoT). Overall, this work introduces an effective paradigm for controllable test-time scaling reasoning.