# Interleaved Reasoning for Large Language Models via Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.19640 · HTML: https://mlsanity.com/paper/2505.19640/

## Key facts

- Cited by 21 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 53 of its 62 references that are in the map.
- First posted on arXiv 26 May 2025.

## 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 53)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [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)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)

## Built on by (most cited first, 21 of 21)

- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [StreamingThinker: Large Language Models Can Think While Reading](https://mlsanity.com/paper/2510.17238/) (2025)
- [CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use](https://mlsanity.com/paper/2602.12268/) (2026)
- [GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization](https://mlsanity.com/paper/2511.15705/) (2025)
- [Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization](https://mlsanity.com/paper/2510.11184/) (2025)
- [Learning from Synthetic Data Improves Multi-hop Reasoning](https://mlsanity.com/paper/2603.02091/) (2026)
- [Learning to Ponder: Adaptive Reasoning in Latent Space](https://mlsanity.com/paper/2509.24238/) (2025)
- [Plantain: Plan-Answer Interleaved Reasoning](https://mlsanity.com/paper/2512.03176/) (2025)
- [When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning](https://mlsanity.com/paper/2605.03314/) (2026)
- [Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education](https://mlsanity.com/paper/2601.14560/) (2026)
- [TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis](https://mlsanity.com/paper/2603.05867/) (2026)
- [Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding](https://mlsanity.com/paper/2608.22429/) (2026)
- [Policy Optimization Prefers The Path of Least Resistance](https://mlsanity.com/paper/2510.21853/) (2025)
- [TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning](https://mlsanity.com/paper/2601.05300/) (2026)
- [PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning](https://mlsanity.com/paper/2602.03190/) (2026)
- [Learning to Learn from Language Feedback with Social Meta-Learning](https://mlsanity.com/paper/2602.16488/) (2026)
- [Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks](https://mlsanity.com/paper/2603.04676/) (2026)
- [DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning](https://mlsanity.com/paper/2605.29568/) (2026)
- [ProactiveLLM: Learning Active Interaction for Streaming Large Language Models](https://mlsanity.com/paper/2606.00523/) (2026)
- [ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction](https://mlsanity.com/paper/2608.13622/) (2026)
- [LLMs are General Asynchronous Agents](https://mlsanity.com/paper/2609.35427/) (2026)

## Abstract (arXiv)

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training paradigm that uses only reinforcement learning (RL) to guide reasoning LLMs to interleave thinking and answering for multi-hop questions. We observe that models inherently possess the ability to perform interleaved reasoning, which can be further enhanced through RL. We introduce a simple yet effective reward scheme to incentivize correct intermediate steps, guiding the policy model toward correct reasoning paths by leveraging intermediate signals generated during interleaved reasoning. Extensive experiments across five diverse datasets and three RL algorithms (PPO, GRPO, and REINFORCE++) demonstrate consistent improvements over traditional think-answer reasoning, without requiring external tools. Our method improves final task accuracy and overall efficiency by enabling more effective credit assignment during RL. Specifically, our approach achieves a 12.5% improvement in Pass@1 accuracy, while reducing overall reasoning length by 37% and TTFT by over 80% on average. Furthermore, our method, trained solely on question answering and logical reasoning datasets, exhibits strong generalization to complex reasoning datasets such as MATH, GPQA, and MMLU. Additionally, we conduct in-depth analysis to reveal several valuable insights into conditional reward modeling.