# Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model

arXiv: https://arxiv.org/abs/2506.23840 · HTML: https://mlsanity.com/paper/2506.23840/

## Key facts

- Cited by 14 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 28 of its 37 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## 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, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.01939/) (2025)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [Learning to Reason under Off-Policy Guidance](https://mlsanity.com/paper/2504.14945/) (2025)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025)
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [CoT-Valve: Length-Compressible Chain-of-Thought Tuning](https://mlsanity.com/paper/2502.09601/) (2025)
- [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://mlsanity.com/paper/2503.05132/) (2025)
- [Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs](https://mlsanity.com/paper/2501.18585/) (2025)
- [Distilling System 2 into System 1](https://mlsanity.com/paper/2407.06023/) (2024)
- [AdaptThink: Reasoning Models Can Learn When to Think](https://mlsanity.com/paper/2505.13417/) (2025)
- [Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.07572/) (2025)
- [C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness](https://mlsanity.com/paper/2412.11664/) (2024)
- [Thinkless: LLM Learns When to Think](https://mlsanity.com/paper/2505.13379/) (2025)
- [Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning](https://mlsanity.com/paper/2504.03380/) (2025)
- [Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL](https://mlsanity.com/paper/2505.10832/) (2025)
- [Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning](https://mlsanity.com/paper/2506.02867/) (2025)
- [Understanding Aha Moments: from External Observations to Internal Mechanisms](https://mlsanity.com/paper/2504.02956/) (2025)
- [Think When You Need: Self-Adaptive Chain-of-Thought Learning](https://mlsanity.com/paper/2504.03234/) (2025)

## Built on by (most cited first, 14 of 14)

- [RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs](https://mlsanity.com/paper/2509.21128/) (2025)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs](https://mlsanity.com/paper/2509.21361/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models](https://mlsanity.com/paper/2606.23181/) (2026)
- [Re2: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving](https://mlsanity.com/paper/2603.07197/) (2026)
- [TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2603.12529/) (2026)
- [Overthinking Loops in Agents: A Structural Risk via MCP Tools](https://mlsanity.com/paper/2602.14798/) (2026)
- [Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models](https://mlsanity.com/paper/2606.15070/) (2026)
- [Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart](https://mlsanity.com/paper/2601.11940/) (2026)
- [Attention Degradation, Function Token Anchoring, and the Limits of Attention-Based Intervention in Large Language Models](https://mlsanity.com/paper/2607.20524/) (2026)
- [PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning](https://mlsanity.com/paper/2605.23074/) (2026)
- [Loose Lips: Understanding Privacy Leakage in Agentic Dialogue](https://mlsanity.com/paper/2610.14071/) (2026)
- [ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.18683/) (2026)

## Abstract (arXiv)

Large Reasoning Models (LRMs) excel at solving complex problems but face an overthinking dilemma. When handling simple tasks, they often produce verbose responses overloaded with thinking tokens (e.g., wait, however). These tokens trigger unnecessary high-level reasoning behaviors like reflection and backtracking, reducing efficiency. In this work, our pilot study reveals that these thinking-token-induced behaviors are not essential for effective problem-solving and may even hinder correct reasoning within constrained token budgets. We identify this phenomenon as the thinking trap. To mitigate this issue, we propose Dual Policy Preference Optimization (DuP-PO), a novel algorithm featuring: (1) A rollout sampling strategy that guarantees balanced exposure to responses with and without thinking tokens; (2) A fine-grained advantage control technique to dynamically regulate the prediction of target tokens; (3) A policy shaping method ensuring stable gradient contributions from thinking tokens. Experimental results on five popular math reasoning benchmarks show that DuP-PO performs well on the popular LRM, which significantly improves their token efficiency during reasoning, while achieving superior performance of the base model.