# Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization

arXiv: https://arxiv.org/abs/2504.21659 · HTML: https://mlsanity.com/paper/2504.21659/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 0 of its 36 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Built on by (most cited first, 30 of 33)

- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025)
- [R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search](https://mlsanity.com/paper/2505.16838/) (2025)
- [VeriThinker: Learning to Verify Makes Reasoning Model Efficient](https://mlsanity.com/paper/2505.17941/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models](https://mlsanity.com/paper/2505.16448/) (2025)
- [Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking](https://mlsanity.com/paper/2509.23392/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning](https://mlsanity.com/paper/2601.22069/) (2026)
- [SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control](https://mlsanity.com/paper/2507.04348/) (2025)
- [ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning](https://mlsanity.com/paper/2601.08310/) (2026)
- [Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models](https://mlsanity.com/paper/2507.02663/) (2025)
- [PEAR: Phase Entropy Aware Reward for Efficient Reasoning](https://mlsanity.com/paper/2510.08026/) (2025)
- [ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code](https://mlsanity.com/paper/2510.08163/) (2025)
- [The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models](https://mlsanity.com/paper/2510.19176/) (2025)
- [Steering Large Reasoning Models towards Concise Reasoning via Flow Matching](https://mlsanity.com/paper/2602.05539/) (2026)
- [Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization](https://mlsanity.com/paper/2508.10164/) (2025)
- [RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning](https://mlsanity.com/paper/2509.25958/) (2025)
- [System 1&2 Synergy via Dynamic Model Interpolation](https://mlsanity.com/paper/2601.21414/) (2026)
- [CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning](https://mlsanity.com/paper/2603.08659/) (2026)
- [Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?](https://mlsanity.com/paper/2510.21007/) (2025)
- [Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models](https://mlsanity.com/paper/2601.09260/) (2026)
- [MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation](https://mlsanity.com/paper/2602.07905/) (2026)
- [QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging](https://mlsanity.com/paper/2601.03506/) (2026)
- [Group Pattern Selection Optimization: Let LRMs Pick the Right Pattern for Reasoning](https://mlsanity.com/paper/2601.07238/) (2026)
- [Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning](https://mlsanity.com/paper/2605.19358/) (2026)
- [BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving](https://mlsanity.com/paper/2606.08684/) (2026)
- [A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM](https://mlsanity.com/paper/2609.07821/) (2026)
- [Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs](https://mlsanity.com/paper/2604.05643/) (2026)

## Abstract (arXiv)

Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using Long-CoT varies across problems: while some problems require elaborate reasoning, others show no improvement, or even degraded accuracy. This motivates adaptive reasoning strategies that tailor reasoning depth to the input. However, prior work primarily reduces redundancy within long reasoning paths, limiting exploration of more efficient strategies beyond the Long-CoT paradigm. To address this, we propose a novel two-stage framework for adaptive and efficient reasoning. First, we construct a hybrid reasoning model by merging long and short CoT models to enable diverse reasoning styles. Second, we apply bi-level preference training to guide the model to select suitable reasoning styles (group-level), and prefer concise and correct reasoning within each style group (instance-level). Experiments demonstrate that our method (Ada-R1) significantly reduces inference costs compared to other baseline approaches, while maintaining performance. Notably, on five mathematical datasets, the average length of reasoning is reduced by more than 50%, highlighting the potential of adaptive strategies to optimize reasoning efficiency in large language models. Our code is coming soon at https://github.com/StarDewXXX/AdaR1