# Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking

arXiv: https://arxiv.org/abs/2503.19602 · HTML: https://mlsanity.com/paper/2503.19602/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 33 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers](https://mlsanity.com/paper/2106.15772/) (2021)
- [Massive Activations in Large Language Models](https://mlsanity.com/paper/2402.17762/) (2024)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [The Impact of Reasoning Step Length on Large Language Models](https://mlsanity.com/paper/2401.04925/) (2024)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse](https://mlsanity.com/paper/2402.09656/) (2024)
- [Context-DPO: Aligning Language Models for Context-Faithfulness](https://mlsanity.com/paper/2412.15280/) (2024)
- [Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models](https://mlsanity.com/paper/2503.15888/) (2025)
- [Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts](https://mlsanity.com/paper/2405.11613/) (2024)
- [SLANG: New Concept Comprehension of Large Language Models](https://mlsanity.com/paper/2401.12585/) (2024)
- [Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness](https://mlsanity.com/paper/2404.00216/) (2024)
- [Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?](https://mlsanity.com/paper/2402.07140/) (2024)
- [HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router](https://mlsanity.com/paper/2410.02684/) (2024)
- [Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject](https://mlsanity.com/paper/2502.06868/) (2025)

## Built on by (most cited first, 20 of 20)

- [FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.24008/) (2025)
- [Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG](https://mlsanity.com/paper/2505.20871/) (2025)
- [a1: Steep Test-time Scaling Law via Environment Augmented Generation](https://mlsanity.com/paper/2504.14597/) (2025)
- [ContextNav: Towards Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2510.04560/) (2025)
- [Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models](https://mlsanity.com/paper/2506.07936/) (2025)
- [Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning](https://mlsanity.com/paper/2509.06461/) (2025)
- [Large Language Models as Computable Approximations to Solomonoff Induction](https://mlsanity.com/paper/2505.15784/) (2025)
- [Gated Differentiable Working Memory for Long-Context Language Modeling](https://mlsanity.com/paper/2601.12906/) (2026)
- [VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG](https://mlsanity.com/paper/2604.05418/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models](https://mlsanity.com/paper/2507.02663/) (2025)
- [Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models](https://mlsanity.com/paper/2601.05693/) (2026)
- [Training-free LLM Verification via Recycling Few-shot Examples](https://mlsanity.com/paper/2506.17251/) (2025)
- [Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models](https://mlsanity.com/paper/2508.03363/) (2025)
- [Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling](https://mlsanity.com/paper/2505.22290/) (2025)
- [Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models](https://mlsanity.com/paper/2605.13338/) (2026)
- [An Asymptotic Theory of Chain-of-Thought in In-Context Learning](https://mlsanity.com/paper/2606.03217/) (2026)
- [LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction](https://mlsanity.com/paper/2606.29407/) (2026)
- [V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure](https://mlsanity.com/paper/2607.21151/) (2026)
- [Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure](https://mlsanity.com/paper/2609.27763/) (2026)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have introduced Reasoning Large Language Models (RLLMs), which employ extended thinking processes with reflection and self-correction capabilities, demonstrating the effectiveness of test-time scaling. RLLMs exhibit innate Chain-of-Thought (CoT) reasoning capability obtained from training, leading to a natural question: "Is CoT prompting, a popular In-Context Learning (ICL) method for chat LLMs, necessary to enhance the reasoning capability of RLLMs?" In this work, we present the first comprehensive analysis of the impacts of Zero-shot CoT and Few-shot CoT on RLLMs across mathematical reasoning tasks. We examine models ranging from 1.5B to 32B parameters, finding that contrary to concerns, CoT prompting significantly enhances RLLMs' performance in most scenarios. Our results reveal distinct patterns: large-capacity models show minimal improvement on simple tasks but substantial gains on complex problems, while smaller models exhibit the opposite behavior. Further analysis demonstrates that CoT prompting effectively controls the distribution of the numbers of thinking tokens and reasoning steps, reducing excessive reflections by approximately 90% in some cases. Moreover, attention logits analysis reveals the RLLMs' overfitting to reflection-related words, which is mitigated by external CoT guidance. Notably, our experiments indicate that for RLLMs, one-shot CoT consistently yields superior performance compared to Few-shot CoT approaches. Our findings provide important insights for optimizing RLLMs' performance through appropriate prompting strategies.