# Schema for In-Context Learning

arXiv: https://arxiv.org/abs/2510.13905 · HTML: https://mlsanity.com/paper/2510.13905/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 38 of its 60 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 38)

- [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)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://mlsanity.com/paper/2310.06117/) (2023)
- [On The Computational Complexity of Self-Attention](https://mlsanity.com/paper/2209.04881/) (2022)
- [Chain of Thoughtlessness? An Analysis of CoT in Planning](https://mlsanity.com/paper/2405.04776/) (2024)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Parallel Context Windows for Large Language Models](https://mlsanity.com/paper/2212.10947/) (2022)
- [Thread of Thought Unraveling Chaotic Contexts](https://mlsanity.com/paper/2311.08734/) (2023)
- [Metacognitive Prompting Improves Understanding in Large Language Models](https://mlsanity.com/paper/2308.05342/) (2023)
- [The broader spectrum of in-context learning](https://mlsanity.com/paper/2412.03782/) (2024)
- [Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPT](https://mlsanity.com/paper/2210.04186/) (2022)
- [TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning](https://mlsanity.com/paper/2505.11737/) (2025)
- [Linking In-context Learning in Transformers to Human Episodic Memory](https://mlsanity.com/paper/2405.14992/) (2024)

## Built on by (most cited first, 4 of 4)

- [ReasonCACHE: Teaching LLMs To Reason Without Weight Updates](https://mlsanity.com/paper/2602.02366/) (2026)
- [Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding](https://mlsanity.com/paper/2605.09271/) (2026)
- [The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content](https://mlsanity.com/paper/2606.11198/) (2026)
- [Who Does This Name Remind You of ? Nationality Prediction via Large Language Model Associative Memory](https://mlsanity.com/paper/2601.12771/) (2026)

## Abstract (arXiv)

In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and transfer at the abstraction level. Inspired by cognitive science, specifically schema theory, which holds that humans interpret new information by activating pre-existing mental frameworks (schemas) to structure understanding, we introduce Schema-Activated In-Context Learning (SA-ICL). This framework extracts the representation of the building blocks of cognition for the reasoning process instilled from prior examples, creating an abstracted schema, a lightweight, structured template of key inferential steps and their relationships, which is then used to augment a model's reasoning process when presented with a novel question. We demonstrate that a broad range of large language models (LLMs) lack the capacity to form and utilize internal schema-based learning representations implicitly, but instead benefit significantly from explicit schema-based scaffolding. Across chemistry and physics questions from the GPQA dataset, our experiments show that SA-ICL consistently boosts performance, up to 36.19 percent, when the single demonstration example is of high quality, which simultaneously reduces reliance on the number of demonstrations and enhances interpretability. Schema-Activated In-Context Learning not only bridges disparate ICL strategies ranging from pattern priming to Chain-of-Thought prompting, but also paves a new path for enhancing human-like reasoning in LLMs.