# Self-Discover: Large Language Models Self-Compose Reasoning Structures

arXiv: https://arxiv.org/abs/2402.03620 · HTML: https://mlsanity.com/paper/2402.03620/

## Key facts

- Cited by 110 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 41 of its 52 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## 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, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [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)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (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)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://mlsanity.com/paper/2310.06117/) (2023)

## Built on by (most cited first, 30 of 110)

- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers](https://mlsanity.com/paper/2408.06195/) (2024)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models](https://mlsanity.com/paper/2406.04271/) (2024)
- [FlowReasoner: Reinforcing Query-Level Meta-Agents](https://mlsanity.com/paper/2504.15257/) (2025)
- [KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents](https://mlsanity.com/paper/2403.03101/) (2024)
- [Atom of Thoughts for Markov LLM Test-Time Scaling](https://mlsanity.com/paper/2502.12018/) (2025)
- [A Survey of Large Language Model Agents for Question Answering](https://mlsanity.com/paper/2503.19213/) (2025)
- [Agents Thinking Fast and Slow: A Talker-Reasoner Architecture](https://mlsanity.com/paper/2410.08328/) (2024)
- [Hogwild! Inference: Parallel LLM Generation via Concurrent Attention](https://mlsanity.com/paper/2504.06261/) (2025)
- [LiteSearch: Efficacious Tree Search for LLM](https://mlsanity.com/paper/2407.00320/) (2024)
- [Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialogues](https://mlsanity.com/paper/2402.13550/) (2024)
- [MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision](https://mlsanity.com/paper/2505.14996/) (2025)
- [Instance-adaptive Zero-shot Chain-of-Thought Prompting](https://mlsanity.com/paper/2409.20441/) (2024)
- [Can LLMs Solve longer Math Word Problems Better?](https://mlsanity.com/paper/2405.14804/) (2024)
- [Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary](https://mlsanity.com/paper/2506.00886/) (2025)
- [Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models](https://mlsanity.com/paper/2404.02575/) (2024)
- [RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues](https://mlsanity.com/paper/2409.12558/) (2024)
- [Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?](https://mlsanity.com/paper/2407.14790/) (2024)
- [ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement](https://mlsanity.com/paper/2410.02108/) (2024)
- [A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2605.07358/) (2026)
- [DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search](https://mlsanity.com/paper/2410.03864/) (2024)
- [P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains](https://mlsanity.com/paper/2410.09207/) (2024)
- [EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models](https://mlsanity.com/paper/2404.12404/) (2024)
- [HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows](https://mlsanity.com/paper/2409.17433/) (2024)
- [MetaScale: Test-Time Scaling with Evolving Meta-Thoughts](https://mlsanity.com/paper/2503.13447/) (2025)
- [Evaluating LLM Reasoning in the Operations Research Domain with ORQA](https://mlsanity.com/paper/2412.17874/) (2024)
- [Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Pot](https://mlsanity.com/paper/2403.11381/) (2024)
- [Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study](https://mlsanity.com/paper/2404.11792/) (2024)

## Abstract (arXiv)

We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a self-discovery process where LLMs select multiple atomic reasoning modules such as critical thinking and step-by-step thinking, and compose them into an explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER substantially improves GPT-4 and PaLM 2's performance on challenging reasoning benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as much as 32% compared to Chain of Thought (CoT). Furthermore, SELF-DISCOVER outperforms inference-intensive methods such as CoT-Self-Consistency by more than 20%, while requiring 10-40x fewer inference compute. Finally, we show that the self-discovered reasoning structures are universally applicable across model families: from PaLM 2-L to GPT-4, and from GPT-4 to Llama2, and share commonalities with human reasoning patterns.