# Reverse Thinking Makes LLMs Stronger Reasoners

arXiv: https://arxiv.org/abs/2411.19865 · HTML: https://mlsanity.com/paper/2411.19865/

## Key facts

- Cited by 29 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 27 of its 62 references that are in the map.
- First posted on arXiv 29 Nov 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, 27 of 27)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [Common 7B Language Models Already Possess Strong Math Capabilities](https://mlsanity.com/paper/2403.04706/) (2024)
- [LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play](https://mlsanity.com/paper/2405.06373/) (2024)
- [RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought](https://mlsanity.com/paper/2305.11499/) (2023)
- [Question Answering and Question Generation as Dual Tasks](https://mlsanity.com/paper/1706.02027/) (2017)
- [SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning](https://mlsanity.com/paper/2406.01006/) (2024)

## Built on by (most cited first, 29 of 29)

- [Baichuan-M1: Pushing the Medical Capability of Large Language Models](https://mlsanity.com/paper/2502.12671/) (2025)
- [On the generalization of language models from in-context learning and finetuning: a controlled study](https://mlsanity.com/paper/2505.00661/) (2025)
- [S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning](https://mlsanity.com/paper/2502.12853/) (2025)
- [SWE-World: Building Software Engineering Agents in Docker-Free Environments](https://mlsanity.com/paper/2602.03419/) (2026)
- [Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models](https://mlsanity.com/paper/2505.10554/) (2025)
- [MetaScale: Test-Time Scaling with Evolving Meta-Thoughts](https://mlsanity.com/paper/2503.13447/) (2025)
- [Learning from Diverse Reasoning Paths with Routing and Collaboration](https://mlsanity.com/paper/2508.16861/) (2025)
- [The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation](https://mlsanity.com/paper/2505.18759/) (2025)
- [Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety](https://mlsanity.com/paper/2506.12482/) (2025)
- [Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models](https://mlsanity.com/paper/2607.14552/) (2026)
- [CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning](https://mlsanity.com/paper/2510.13166/) (2025)
- [Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning](https://mlsanity.com/paper/2603.27820/) (2026)
- [SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation](https://mlsanity.com/paper/2506.06470/) (2025)
- [Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection](https://mlsanity.com/paper/2601.09692/) (2026)
- [TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction](https://mlsanity.com/paper/2602.11700/) (2026)
- [Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility](https://mlsanity.com/paper/2605.29229/) (2026)
- [Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions](https://mlsanity.com/paper/2501.01872/) (2025)
- [RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles](https://mlsanity.com/paper/2501.13491/) (2025)
- [Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement](https://mlsanity.com/paper/2504.09058/) (2025)
- [Reverse Thinking Enhances Missing Information Detection in Large Language Models](https://mlsanity.com/paper/2512.10273/) (2025)
- [Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion](https://mlsanity.com/paper/2603.19266/) (2026)
- [GRP: Goal-Reversed Prompting for Zero-Shot Evaluation with LLMs](https://mlsanity.com/paper/2503.06139/) (2025)
- [Fusing Bidirectional Chains of Thought and Reward Mechanisms A Method for Enhancing Question-Answering Capabilities of Large Language Models for Chinese Intangible Cultural Heritage](https://mlsanity.com/paper/2505.08167/) (2025)
- [VLMs Can Aggregate Scattered Training Patches](https://mlsanity.com/paper/2506.03614/) (2025)
- [Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2511.09109/) (2025)
- [Generating Verifiable Chain of Thoughts from Exection-Traces](https://mlsanity.com/paper/2512.00127/) (2025)
- [DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization](https://mlsanity.com/paper/2605.10863/) (2026)
- [The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes](https://mlsanity.com/paper/2606.11470/) (2026)
- [Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability](https://mlsanity.com/paper/2609.24760/) (2026)

## Abstract (arXiv)

Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning performance as it enables consistency checks between their forward and backward thinking. To enable Large Language Models (LLMs) to perform reverse thinking, we introduce Reverse-Enhanced Thinking (RevThink), a framework composed of data augmentation and learning objectives. In RevThink, we augment the dataset by collecting structured forward-backward reasoning from a teacher model, consisting of: (1) the original question, (2) forward reasoning, (3) backward question, and (4) backward reasoning. We then employ three objectives to train a smaller student model in a multi-task learning fashion: (a) generate forward reasoning from a question, (b) generate a backward question from a question, and (c) generate backward reasoning from the backward question. Experiments across 12 datasets covering commonsense, math, and logical reasoning show an average 13.53% improvement over the student model's zero-shot performance and a 6.84% improvement over the strongest knowledge distillation baselines. Moreover, our method demonstrates sample efficiency -- using only 10% of the correct forward reasoning from the training data, it outperforms a standard fine-tuning method trained on 10x more forward reasoning. RevThink also exhibits strong generalization to out-of-distribution held-out datasets.