# DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF

arXiv: https://arxiv.org/abs/2511.19097 · HTML: https://mlsanity.com/paper/2511.19097/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 26 of 26)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [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)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style](https://mlsanity.com/paper/2410.16184/) (2024)
- [LLM Critics Help Catch LLM Bugs](https://mlsanity.com/paper/2407.00215/) (2024)
- [HelpSteer2-Preference: Complementing Ratings with Preferences](https://mlsanity.com/paper/2410.01257/) (2024)
- [Self-Generated Critiques Boost Reward Modeling for Language Models](https://mlsanity.com/paper/2411.16646/) (2024)
- [RMB: Comprehensively Benchmarking Reward Models in LLM Alignment](https://mlsanity.com/paper/2410.09893/) (2024)
- [DABERT: Dual Attention Enhanced BERT for Semantic Matching](https://mlsanity.com/paper/2210.03454/) (2022)
- [Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance](https://mlsanity.com/paper/2508.21741/) (2025)
- [Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling](https://mlsanity.com/paper/2509.25361/) (2025)

## Built on by (most cited first, 7 of 7)

- [Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models](https://mlsanity.com/paper/2604.10079/) (2026)
- [Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty](https://mlsanity.com/paper/2604.10072/) (2026)
- [DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning](https://mlsanity.com/paper/2601.17777/) (2026)
- [Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning](https://mlsanity.com/paper/2604.14010/) (2026)
- [Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering](https://mlsanity.com/paper/2602.19569/) (2026)
- [Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization](https://mlsanity.com/paper/2604.17051/) (2026)
- [Multi-Granularity Reasoning for Natural Language Inference](https://mlsanity.com/paper/2606.05181/) (2026)

## Abstract (arXiv)

Existing reinforcement learning methods for Chain-of-Thought reasoning suffer from two critical limitations. First, they operate as monolithic black boxes that provide undifferentiated reward signals, obscuring individual step contributions and hindering error diagnosis. Second, sequential decoding has O(n) time complexity. This makes real-time deployment impractical for complex reasoning tasks. We present DeCoRL (Decoupled Reasoning Chains via Coordinated Reinforcement Learning), a novel framework that transforms reasoning from sequential processing into collaborative modular orchestration. DeCoRL trains lightweight specialized models to generate reasoning sub-steps concurrently, eliminating sequential bottlenecks through parallel processing. To enable precise error attribution, the framework designs modular reward functions that score each sub-step independently. Cascaded DRPO optimization then coordinates these rewards while preserving inter-step dependencies. Comprehensive evaluation demonstrates state-of-the-art results across RM-Bench, RMB, and RewardBench, outperforming existing methods including large-scale models. DeCoRL delivers 3.8 times faster inference while maintaining superior solution quality and offers a 22.7% improvement in interpretability through explicit reward attribution. These advancements, combined with a 72.4% reduction in energy consumption and a 68% increase in throughput, make real-time deployment of complex reasoning systems a reality.