# When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling

arXiv: https://arxiv.org/abs/2604.10739 · HTML: https://mlsanity.com/paper/2604.10739/

## Key facts

- Cited by 16 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 14 of its 26 references that are in the map.
- First posted on arXiv 12 Apr 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, 14 of 14)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [The Right Tool for the Job: Matching Model and Instance Complexities](https://mlsanity.com/paper/2004.07453/) (2020)
- [Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models](https://mlsanity.com/paper/2506.04210/) (2025)
- [Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering](https://mlsanity.com/paper/2502.13962/) (2025)
- [Do LLMs Really Need 10+ Thoughts for "Find the Time 1000 Days Later"? Towards Structural Understanding of LLM Overthinking](https://mlsanity.com/paper/2510.07880/) (2025)
- [Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models](https://mlsanity.com/paper/2507.04023/) (2025)

## Built on by (most cited first, 16 of 16)

- [SCOPE-RL: Optimizing Reasoning Paths Before and After Success](https://mlsanity.com/paper/2607.11506/) (2026)
- [LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications](https://mlsanity.com/paper/2608.23058/) (2026)
- [It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories](https://mlsanity.com/paper/2609.03436/) (2026)
- [Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs](https://mlsanity.com/paper/2604.16753/) (2026)
- [State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning](https://mlsanity.com/paper/2605.00206/) (2026)
- [CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing](https://mlsanity.com/paper/2605.14084/) (2026)
- [Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning](https://mlsanity.com/paper/2606.01682/) (2026)
- [Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey](https://mlsanity.com/paper/2606.08500/) (2026)
- [Solver-Hard Is Not Model-Hard: A Hardness-Controlled Diagnostic for LLM Constraint Reasoning](https://mlsanity.com/paper/2607.17047/) (2026)
- [Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AI](https://mlsanity.com/paper/2608.26442/) (2026)
- [InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language Models](https://mlsanity.com/paper/2609.04014/) (2026)
- [LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents](https://mlsanity.com/paper/2609.30662/) (2026)
- [MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller](https://mlsanity.com/paper/2609.37304/) (2026)
- [Knowing the Rules, Applying the Rules: Evaluating Language Models on Traditional Chinese Bazi](https://mlsanity.com/paper/2610.05682/) (2026)
- [Whose turn is it? Context-guided model routing for stateful agents](https://mlsanity.com/paper/2610.19292/) (2026)
- [RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer](https://mlsanity.com/paper/2610.19872/) (2026)

## Abstract (arXiv)

Scaling test-time compute through extended chains of thought has become a dominant paradigm for improving large language model reasoning. However, existing research implicitly assumes that longer thinking always yields better results. This assumption remains largely unexamined. We systematically investigate how the marginal utility of additional reasoning tokens changes as compute budgets increase. We find that marginal returns diminish substantially at higher budgets and that models exhibit ``overthinking'', where extended reasoning is associated with abandoning previously correct answers. Furthermore, we show that optimal thinking length varies across problem difficulty, suggesting that uniform compute allocation is suboptimal. Our cost-aware evaluation framework reveals that stopping at moderate budgets can reduce computation significantly while maintaining comparable accuracy.