mlsanityData to 14 Oct 2026

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

arXiv 2505.24863 ↗First posted 30 May 2025cs.CLcited by 29

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

This paper presents AlphaOne (α1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. α1 first introduces α moment, which represents the scaled thinking phase with a universal parameter α. Within this scaled pre-α moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the α moment, α1 deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoning and efficient answer generation. This approach unifies and generalizes existing monotonic scaling methods by enabling flexible and dense slow-to-fast reasoning modulation. Extensive empirical studies on various challenging benchmarks across mathematical, coding, and scientific domains demonstrate α1's superior reasoning capability and efficiency. Project page: https://alphaone-project.github.io/

Key facts. Cited by 29 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 39 of its 84 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

39 of 84 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs30 Apr
  2. 2025Dynamic Early Exit in Reasoning Models22 Apr
  3. 2025THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models17 Apr
  4. 2025Reasoning Models Can Be Effective Without Thinking14 Apr
  5. 2025Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time12 Apr
  6. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  7. 2025Scalable Best-of-N Selection for Large Language Models via Self-Certainty25 Feb
  8. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning25 Feb
  9. 2025Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?17 Feb
  10. 2025Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning1 Feb
  11. 2025s1: Simple test-time scaling31 Jan
  12. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs30 Jan
5 more
  1. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  2. 2024O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?25 Nov
  3. 2024TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling18 Oct
  4. 2024Interpretable Contrastive Monte Carlo Tree Search Reasoning2 Oct
  5. 2024Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling30 Aug

Other references · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2024OpenAI o1 System Cardcited by 1,244
  7. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  8. 2022Solving math word problems with process- and outcome-based feedbackcited by 901
  9. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  10. 2024Phi-4 Technical Reportcited by 711
  11. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  12. 2025TTRL: Test-Time Reinforcement Learningcited by 275
10 more
  1. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 221
  2. 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoTcited by 166
  3. 2024LLaVA-Critic: Learning to Evaluate Multimodal Modelscited by 134
  4. 2025Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuningcited by 123
  5. 2025Perception-R1: Pioneering Perception Policy with Reinforcement Learningcited by 120
  6. 2025S*: Test Time Scaling for Code Generationcited by 98
  7. 2024Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreakscited by 48
  8. 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulationcited by 46
  9. 2024Slow Perception: Let's Perceive Geometric Figures Step-by-stepcited by 24
  10. 2025Perception in Reflectioncited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 14.

29 papers.

Sort:

By area:

  1. 2025OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Modelscited by 114
  2. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecyclecited by 35
  3. 2025Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoningcited by 34
  4. 2026LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signalscited by 24
  5. 2025Towards Concise and Adaptive Thinking in Large Reasoning Models: A Surveycited by 18
  6. 2025Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoningcited by 16
  7. 2026Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probingcited by 14
  8. 2025Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Teamcited by 13
  9. 2025Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughtscited by 12
  10. 2025From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Modelscited by 12
  11. 2025DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inferencecited by 11
  12. 2026LLMs Improving LLMs: Agentic Discovery for Test-Time Scalingcited by 10
17 more
  1. 2025On The Fragility of Benchmark Contamination Detection in Reasoning Modelscited by 9
  2. 2026Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Modelscited by 8
  3. 2026FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Modelscited by 8
  4. 2025CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Schedulingcited by 5
  5. 2026Steering Large Reasoning Models towards Concise Reasoning via Flow Matchingcited by 4
  6. 2025Learning to Reason with Mixture of Tokenscited by 3
  7. 2025DecepChain: Inducing Deceptive Reasoning in Large Language Modelscited by 3
  8. 2025MixReasoning: Switching Modes to Thinkcited by 3
  9. 2025When Reasoning Meets Its Lawscited by 3
  10. 2026To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Taskscited by 2
  11. 2026TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RLcited by 2
  12. 2026Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scalingcited by 2
  13. 2026Oops, Wait: Discourse Tokens Matter in Reasoning Modelcited by 1
  14. 2026Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learningcited by 0
  15. 2026Risky Business: Measuring The Faithfulness-Safety Tensioncited by 0
  16. 2026Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoningcited by 0
  17. 2026Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correctioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
  2. 2026ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
  3. 2025OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
  4. 2025Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
  5. 2026APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
  6. 2025From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
  7. 2026Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models
  8. 2026Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models