# Reverse-Engineered Reasoning for Open-Ended Generation

arXiv: https://arxiv.org/abs/2509.06160 · HTML: https://mlsanity.com/paper/2509.06160/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## Builds on (most cited first, 30 of 32)

- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning](https://mlsanity.com/paper/2504.08837/) (2025)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset](https://mlsanity.com/paper/2402.10176/) (2024)
- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [Reinforcing General Reasoning without Verifiers](https://mlsanity.com/paper/2505.21493/) (2025)
- [ALIP: Adaptive Language-Image Pre-training with Synthetic Caption](https://mlsanity.com/paper/2308.08428/) (2023)
- [HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models](https://mlsanity.com/paper/2409.16191/) (2024)
- [Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning](https://mlsanity.com/paper/2509.03646/) (2025)
- [To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization](https://mlsanity.com/paper/2502.00691/) (2025)
- [FastMCTS: A Simple Sampling Strategy for Data Synthesis](https://mlsanity.com/paper/2502.11476/) (2025)
- [Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning](https://mlsanity.com/paper/2306.07106/) (2023)

## Built on by (most cited first, 30 of 34)

- [Scaling Latent Reasoning via Looped Language Models](https://mlsanity.com/paper/2510.25741/) (2025)
- [Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning](https://mlsanity.com/paper/2511.16043/) (2025)
- [RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation](https://mlsanity.com/paper/2601.08430/) (2026)
- [ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking](https://mlsanity.com/paper/2601.06487/) (2026)
- [RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time](https://mlsanity.com/paper/2604.11626/) (2026)
- [From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning](https://mlsanity.com/paper/2511.23031/) (2025)
- [RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models](https://mlsanity.com/paper/2510.25206/) (2025)
- [Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation](https://mlsanity.com/paper/2607.05382/) (2026)
- [Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning](https://mlsanity.com/paper/2605.14054/) (2026)
- [DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing](https://mlsanity.com/paper/2601.09609/) (2026)
- [FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation](https://mlsanity.com/paper/2602.22273/) (2026)
- [MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier](https://mlsanity.com/paper/2603.03756/) (2026)
- [Learning to Reason as Action Abstractions with Scalable Mid-Training RL](https://mlsanity.com/paper/2509.25810/) (2025)
- [ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning](https://mlsanity.com/paper/2510.18250/) (2025)
- [CogDoc: Towards Unified thinking in Documents](https://mlsanity.com/paper/2512.12658/) (2025)
- [AIR: Post-training Data Selection for Reasoning via Attention Head Influence](https://mlsanity.com/paper/2512.13279/) (2025)
- [From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair](https://mlsanity.com/paper/2601.23257/) (2026)
- [R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning](https://mlsanity.com/paper/2604.03004/) (2026)
- [Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation](https://mlsanity.com/paper/2602.14469/) (2026)
- [ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding](https://mlsanity.com/paper/2604.06685/) (2026)
- [PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation](https://mlsanity.com/paper/2601.14903/) (2026)
- [Prompt-Level Reward Specifications for Open-Ended Post-Training](https://mlsanity.com/paper/2605.29275/) (2026)
- [SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories](https://mlsanity.com/paper/2608.09799/) (2026)
- [Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation](https://mlsanity.com/paper/2608.30397/) (2026)
- [CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop](https://mlsanity.com/paper/2512.11480/) (2025)
- [A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement](https://mlsanity.com/paper/2603.20441/) (2026)
- [Triviality Corrected Endogenous Reward](https://mlsanity.com/paper/2604.11522/) (2026)
- [Mind DeepResearch Technical Report](https://mlsanity.com/paper/2604.14518/) (2026)
- [Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth](https://mlsanity.com/paper/2605.18603/) (2026)
- [IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking](https://mlsanity.com/paper/2606.09709/) (2026)

## Abstract (arXiv)

While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning -- reinforcement learning (RL) and instruction distillation -- falter in this area; RL struggles with the absence of clear reward signals and high-quality reward models, while distillation is prohibitively expensive and capped by the teacher model's capabilities. To overcome these limitations, we introduce REverse-Engineered Reasoning (REER), a new paradigm that fundamentally shifts the approach. Instead of building a reasoning process ``forwards'' through trial-and-error or imitation, REER works ``backwards'' from known-good solutions to computationally discover the latent, step-by-step deep reasoning process that could have produced them. Using this scalable, gradient-free approach, we curate and open-source DeepWriting-20K, a large-scale dataset of 20,000 deep reasoning trajectories for open-ended tasks. Our model, DeepWriter-8B, trained on this data, not only surpasses strong open-source baselines but also achieves performance competitive with, and at times superior to, leading proprietary models like GPT-4o and Claude 3.5.