Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

• URL: http://arxiv.org/abs/2605.13511v1
• Date: Wed, 13 May 2026 13:30:12 GMT
• Title: Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
• Abstract summary: In-context learning (ICL) adapts large language models to new tasks by conditioning on demonstrations in the prompt without parameter updates.<n>We study many-shot chain-of-thought in-context learning (CoT-ICL) for reasoning and show that standard many-shot rules do not transfer.
• Score: 58.439517684779936
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In-context learning (ICL) adapts large language models (LLMs) to new tasks by conditioning on demonstrations in the prompt without parameter updates. With long-context models, many-shot ICL can use dozens to hundreds of examples and achieve performance comparable to fine-tuning, yet current understanding of its scaling behavior is largely derived from non-reasoning tasks. We study many-shot chain-of-thought in-context learning (CoT-ICL) for reasoning and show that standard many-shot rules do not transfer. Across non-reasoning and reasoning-oriented LLMs and across non-reasoning and reasoning tasks, we find: (i) a setting-dependent scaling effect, where increasing the number of CoT demonstrations is unstable for non-reasoning LLMs and benefits mainly reasoning-oriented LLMs; (ii) similarity-based retrieval helps on non-reasoning tasks but fails on reasoning, since semantic similarity poorly predicts procedural (i.e., CoT) compatibility; and (iii) an order-scaling effect, where performance variance grows with more CoT demonstrations. We interpret these behaviors by viewing many-shot CoT-ICL as in-context test-time learning rather than scaled pattern matching, and suggests two principles: (i) demonstrations should be easy for the target model to understand, and (ii) they should be ordered to support a smooth conceptual progression. Guided by the principle, we propose Curvilinear Demonstration Selection (CDS), a simple ordering method that yields up to a 5.42 percentage-point gain on geometry with 64 demonstrations. Overall, our results reframe the long context window from a retrieval buffer into a structured curriculum for in-context test-time learning.

Related papers

• ACIL: Auto Chain of Thoughts for In-Context Learning [1.4262320227703154]
  This paper introduces an Automatic Chain-of-Thought (Auto-CoT) framework to improve In-Context Learning (ICL)<n>Auto-CoT generates reasoning chains for input-output examples, augments the prompt context with structured intermediate explanations, and removes irrelevant or low-quality demonstrations.<n> Experiments across multiple reasoning tasks demonstrate that the proposed framework improves ICL performance by providing explicit intermediate reasoning guidance.
  arXiv  Detail & Related papers  (2026-05-16T17:10:13Z)
• UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomy [99.95663439922937]
  In-context Learning efficacy is often non-monotonic and highly task-dependent.<n>We introduce a six-level capability-oriented taxonomy that categorizes the functional role of demonstrations.<n>We construct UniICL-760K, a large-scale corpus featuring curated 8-shot In-context Learning episodes.<n>As an architectural intervention, we propose the Context-Adaptive Prototype Modulator.
  arXiv  Detail & Related papers  (2026-03-25T18:09:33Z)
• Parallel In-context Learning for Large Vision Language Models [17.034369186373162]
  Large vision-language models (LVLMs) employ multi-modal in-context learning (MM-ICL) to adapt to new tasks by leveraging demonstration examples.<n>We propose Parallel In-Context Learning (Parallel-ICL), a plug-and-play inference algorithm.<n>We show that Parallel-ICL achieves performance comparable to full-context MM-ICL, while significantly improving inference speed.
  arXiv  Detail & Related papers  (2026-03-17T03:28:36Z)
• Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought [15.598263332303612]
  Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks.<n>This study dives into the foundations of these observations by addressing three critical questions.
  arXiv  Detail & Related papers  (2026-02-16T10:57:26Z)
• UniT: Unified Multimodal Chain-of-Thought Test-time Scaling [85.590774707406]
  Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs.<n>We introduce UniT, a framework for multimodal test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds.
  arXiv  Detail & Related papers  (2026-02-12T18:59:49Z)
• CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs [33.63911145333626]
  Chain-of-Thought prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models.<n>Existing implementations, such as in-context learning and fine-tuning, remain costly and inefficient.<n>We introduce CoT Vectors, compact representations that encode task-general, multi-step reasoning knowledge.
  arXiv  Detail & Related papers  (2025-10-01T06:58:23Z)
• ParaICL: Towards Parallel In-Context Learning [74.38022919598443]
  Large language models (LLMs) have become the norm in natural language processing.<n>Few-shot in-context learning (ICL) relies on the choice of few-shot demonstration examples.<n>We propose a novel method named parallel in-context learning (ParaICL)
  arXiv  Detail & Related papers  (2024-03-31T05:56:15Z)
• TEGEE: Task dEfinition Guided Expert Ensembling for Generalizable and Few-shot Learning [37.09785060896196]
  We propose textbfTEGEE (Task Definition Guided Expert Ensembling), a method that explicitly extracts task definitions.<n>Our framework employs a dual 3B model approach, with each model assigned a distinct role.<n> Empirical evaluations show that TEGEE performs comparably to the larger LLaMA2-13B model.
  arXiv  Detail & Related papers  (2024-03-07T05:26:41Z)
• Scaling In-Context Demonstrations with Structured Attention [75.41845145597875]
  We propose a better architectural design for in-context learning. Structured Attention for In-Context Learning replaces the full-attention by a structured attention mechanism. We show that SAICL achieves comparable or better performance than full attention while obtaining up to 3.4x inference speed-up.
  arXiv  Detail & Related papers  (2023-07-05T23:26:01Z)
• Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models [81.01397924280612]
  Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains.
  arXiv  Detail & Related papers  (2023-04-23T13:54:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.