To Think or Not to Think: Allocating Reasoning Where It Helps

arXiv:2609.29664 · cs.AI · Submitted 2026-08-30 · Read on arXiv

cs.AI

Submitted: 2026-08-30

Updated: 2026-08-30

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 159× in this paper · explained in 1 episode
• GRPO — 73× in this paper · explained in 6 episodes
• Benchmark — 30× in this paper · explained in 2 episodes
• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Reasoning Traces — 3× in this paper · explained in 3 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adaptive Reasoning — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Contrastive Accuracy Reward Estimation — 2× in this paper
• Cyclic Reasoning Ratio — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 24 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Verifiable Rewards — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
• Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
• Training Language Models to Reason Efficiently
• Evaluating Large Language Models Trained on Code
• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
• Training Verifiers to Solve Math Word Problems
• Stable Reinforcement Learning for Efficient Reasoning
• Thinkless: LLM Learns When to Think
• Measuring Mathematical Problem Solving With the MATH Dataset
• ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
• OpenAI o1 System Card
• Training Language Models to Self-Correct via Reinforcement Learning
• Decoupled Weight Decay Regularization
• The Expressive Power of Transformers with Chain of Thought
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
• Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
• Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems