# Strategy-Induct: Task-Level Strategy Induction for Instruction Generation

arXiv: https://arxiv.org/abs/2605.20924 · HTML: https://mlsanity.com/paper/2605.20924/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 19 of 19)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Instruction Induction: From Few Examples to Natural Language Task Descriptions](https://mlsanity.com/paper/2205.10782/) (2022)
- [Self-Discover: Large Language Models Self-Compose Reasoning Structures](https://mlsanity.com/paper/2402.03620/) (2024)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [AutoHint: Automatic Prompt Optimization with Hint Generation](https://mlsanity.com/paper/2307.07415/) (2023)
- [Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning](https://mlsanity.com/paper/2407.01687/) (2024)
- [Temporal Knowledge Question Answering via Abstract Reasoning Induction](https://mlsanity.com/paper/2311.09149/) (2023)
- [IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction](https://mlsanity.com/paper/2408.10455/) (2024)
- [Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models](https://mlsanity.com/paper/2310.13127/) (2023)
- [Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation](https://mlsanity.com/paper/2409.03271/) (2024)
- [MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models](https://mlsanity.com/paper/2410.09542/) (2024)
- [Auto-Evolve: Enhancing Large Language Model's Performance via Self-Reasoning Framework](https://mlsanity.com/paper/2410.06328/) (2024)
- [Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning](https://mlsanity.com/paper/2602.08028/) (2026)

## Abstract (arXiv)

Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing approaches often rely on input-output pairs, where obtaining labeled answers can be difficult or costly. To address this limitation, we propose Strategy-Induct, a framework that derives task-level instructions solely from a small set of example questions without requiring labeled answers. Our approach first prompts the model to generate explicit reasoning strategies for each question, forming (strategy, question) pairs. These pairs are then used to induce a task instruction that guides reasoning. Experiments across multiple tasks and model scales demonstrate that Strategy-Induct outperforms state-of-the-art methods in question-only settings. Furthermore, we observe that jointly utilizing LLMs and Large Reasoning Models across task instruction generation and inference may lead to further performance improvements.