mlsanityData to 14 Oct 2026

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models

arXiv 2505.17312 ↗First posted 22 May 2025cs.AI cs.LGcited by 17

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

Abstract (arXiv)

LLMs often need effective configurations, like temperature and reasoning steps, to handle tasks requiring sophisticated reasoning and problem-solving, ranging from joke generation to mathematical reasoning. Existing prompting approaches usually adopt general-purpose, fixed configurations that work 'well enough' across tasks but seldom achieve task-specific optimality. To address this gap, we introduce AdaReasoner, an LLM-agnostic plugin designed for any LLM to automate adaptive reasoning configurations for tasks requiring different types of thinking. AdaReasoner is trained using a reinforcement learning (RL) framework, combining a factorized action space with a targeted exploration strategy, along with a pretrained reward model to optimize the policy model for reasoning configurations with only a few-shot guide. AdaReasoner is backed by theoretical guarantees and experiments of fast convergence and a sublinear policy gap. Across six different LLMs and a variety of reasoning tasks, it consistently outperforms standard baselines, preserves out-of-distribution robustness, and yield gains on knowledge-intensive tasks through tailored prompts.

Key facts. Cited by 17 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 30 of its 62 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

30 of 62 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o115 Feb
  2. 2024Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability29 Nov

Other references · 28

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  4. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  5. 2024OpenAI o1 System Cardcited by 1,244
  6. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
  7. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  8. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
  9. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 263
  10. 2023Reward Design with Language Modelscited by 261
  11. 2023SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Modelscited by 256
  12. 2023Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learningcited by 165
16 more
  1. 2024The Impact of Reasoning Step Length on Large Language Modelscited by 153
  2. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  3. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worsecited by 109
  4. 2023Towards Mitigating Hallucination in Large Language Models via Self-Reflectioncited by 81
  5. 2020LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoningcited by 69
  6. 2023Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learningcited by 69
  7. 2024MedExQA: Medical Question Answering Benchmark with Multiple Explanationscited by 60
  8. 2024How to think step-by-step: A mechanistic understanding of chain-of-thought reasoningcited by 53
  9. 2024Metaphor Understanding Challenge Dataset for LLMscited by 30
  10. 2025BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languagescited by 27
  11. 2023Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruningcited by 26
  12. 2023In-context Learning Generalizes, But Not Always Robustly: The Case of Syntaxcited by 22
  13. 2019Reinforcement Learning with Dynamic Boltzmann Softmax Updatescited by 14
  14. 2023CRoW: Benchmarking Commonsense Reasoning in Real-World Taskscited by 8
  15. 2024Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Taskscited by 8
  16. 2024LLM can Achieve Self-Regulation via Hyperparameter Aware Generationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 8.

17 papers.

Sort:

By area:

  1. 2025Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variationcited by 45
  2. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMscited by 31
  3. 2025Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoningcited by 22
  4. 2025Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Studycited by 17
  5. 2025From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Modelscited by 12
  6. 2025RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMscited by 6
  7. 2025Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanismcited by 4
  8. 2026Synthetic Interaction Data for Scalable Personalization in Large Language Modelscited by 4
  9. 2026Distribution-Aware Reward Estimation for Test-Time Reinforcement Learningcited by 3
  10. 2026Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Datacited by 2
  11. 2025CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMscited by 1
  12. 2025ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Bettercited by 1
5 more
  1. 2026Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questionscited by 1
  2. 2026HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reductioncited by 0
  3. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMscited by 0
  4. 2026FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agentscited by 0
  5. 2026Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinkingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AdaR: A Framework for Equipping LLMs with Adaptive Reasoning
  2. 2025AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
  3. 2025AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
  4. 2026RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering
  5. 2025QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
  6. 2023TART: A plug-and-play Transformer module for task-agnostic reasoning
  7. 2025Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
  8. 2025Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize?