# DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models

arXiv: https://arxiv.org/abs/2606.23181 · HTML: https://mlsanity.com/paper/2606.23181/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning](https://mlsanity.com/paper/2408.13457/) (2024)
- [SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning](https://mlsanity.com/paper/2505.11274/) (2025)
- [Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs](https://mlsanity.com/paper/2507.02076/) (2025)
- [Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence](https://mlsanity.com/paper/2604.24954/) (2026)
- [Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection](https://mlsanity.com/paper/2505.19435/) (2025)
- [Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model](https://mlsanity.com/paper/2506.23840/) (2025)
- [Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?](https://mlsanity.com/paper/2510.12680/) (2025)
- [Hierarchical Budget Policy Optimization for Adaptive Reasoning](https://mlsanity.com/paper/2507.15844/) (2025)

## Built on by (most cited first, 8 of 8)

- [Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models](https://mlsanity.com/paper/2607.28166/) (2026)
- [Faster Block-Diffusion Serving with Distribution-Free Risk Guarantees](https://mlsanity.com/paper/2609.33887/) (2026)
- [Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding](https://mlsanity.com/paper/2609.33889/) (2026)
- [Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks](https://mlsanity.com/paper/2609.37493/) (2026)
- [CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters](https://mlsanity.com/paper/2610.00321/) (2026)
- [Distilling Directional Verification](https://mlsanity.com/paper/2610.00997/) (2026)
- [What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects](https://mlsanity.com/paper/2610.05533/) (2026)
- [When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation](https://mlsanity.com/paper/2610.12061/) (2026)

## Abstract (arXiv)

Hybrid reasoning models can answer directly or spend extra tokens on extended thinking. A practical router should choose between these modes for each query, so easy problems avoid unnecessary reasoning and hard problems receive enough budget to finish the answer. Existing routers move in this direction, but they typically require labeled training data or fix thinking budgets up front, ignoring answer-level evidence from the model itself. We introduce DART, a training-free routing framework that samples two cheap no-think drafts, accepts direct answering when the drafts agree, and predicts a thinking budget from draft entropy when they disagree. Across the main comparisons, DART preserves or improves always-thinking accuracy in most settings while reducing thinking-token use. Accuracy improves by up to +9.0 points on Olympiad-level math and by up to +22.5 points on code under execution-based equivalence, while thinking-token use drops by 32-73%. The Stage~1 signal extends across model scales (0.6B--32B), model families, and API-only hosted settings, with no labeled data and no gradient updates required. Our code is available at https://github.com/js-lee-AI/DART.