100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models

• URL: http://arxiv.org/abs/2505.00551v1
• Date: Thu, 01 May 2025 14:28:35 GMT
• Title: 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
• Authors: Chong Zhang, Yue Deng, Xiang Lin, Bin Wang, Dianwen Ng, Hai Ye, Xingxuan Li, Yao Xiao, Zhanfeng Mo, Qi Zhang, Lidong Bing,
• Abstract summary: The recent release of DeepSeek-R1 has generated widespread social impact and sparked enthusiasm in the research community for exploring the explicit reasoning paradigm of language models.<n>The implementation details of the released models have not been fully open-sourced by DeepSeek, including DeepSeek-R1-Zero, DeepSeek-R1, and the distilled small models.<n>Many replication studies have emerged aiming to reproduce the strong performance achieved by DeepSeek-R1, reaching comparable performance through similar training procedures and fully open-source data resources.
• Score: 58.98176123850354
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent development of reasoning language models (RLMs) represents a novel evolution in large language models. In particular, the recent release of DeepSeek-R1 has generated widespread social impact and sparked enthusiasm in the research community for exploring the explicit reasoning paradigm of language models. However, the implementation details of the released models have not been fully open-sourced by DeepSeek, including DeepSeek-R1-Zero, DeepSeek-R1, and the distilled small models. As a result, many replication studies have emerged aiming to reproduce the strong performance achieved by DeepSeek-R1, reaching comparable performance through similar training procedures and fully open-source data resources. These works have investigated feasible strategies for supervised fine-tuning (SFT) and reinforcement learning from verifiable rewards (RLVR), focusing on data preparation and method design, yielding various valuable insights. In this report, we provide a summary of recent replication studies to inspire future research. We primarily focus on SFT and RLVR as two main directions, introducing the details for data construction, method design and training procedure of current replication studies. Moreover, we conclude key findings from the implementation details and experimental results reported by these studies, anticipating to inspire future research. We also discuss additional techniques of enhancing RLMs, highlighting the potential of expanding the application scope of these models, and discussing the challenges in development. By this survey, we aim to help researchers and developers of RLMs stay updated with the latest advancements, and seek to inspire new ideas to further enhance RLMs.

Related papers

• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning [11.872929831119661]
  We introduce RAG-RL, the first reasoning language model (RLM) specifically trained for retrieval-augmented generation (RAG) settings.<n>RAG-RL demonstrates that stronger answer generation models can identify relevant contexts within larger sets of retrieved information.<n>We show that curriculum design in the reinforcement learning (RL) post-training process is a powerful approach to enhancing model performance.
  arXiv  Detail & Related papers  (2025-03-17T02:53:42Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models. Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start. Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Generative Large Recommendation Models: Emerging Trends in LLMs for Recommendation [85.52251362906418]
  This tutorial explores two primary approaches for integrating large language models (LLMs) It provides a comprehensive overview of generative large recommendation models, including their recent advancements, challenges, and potential research directions. Key topics include data quality, scaling laws, user behavior mining, and efficiency in training and inference.
  arXiv  Detail & Related papers  (2025-02-19T14:48:25Z)
• Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models [33.13238566815798]
  Large Language Models (LLMs) have sparked significant research interest in leveraging them to tackle complex reasoning tasks. Recent studies demonstrate that encouraging LLMs to "think" with more tokens during test-time inference can significantly boost reasoning accuracy. The introduction of OpenAI's o1 series marks a significant milestone in this research direction.
  arXiv  Detail & Related papers  (2025-01-16T17:37:58Z)
• Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
  o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research.<n>We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
  arXiv  Detail & Related papers  (2024-11-18T16:15:17Z)
• A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions [0.0]
  RAG combines retrieval mechanisms with generative language models to enhance the accuracy of outputs. Recent research breakthroughs are discussed, highlighting novel methods for improving retrieval efficiency. Future research directions are proposed, focusing on improving the robustness of RAG models.
  arXiv  Detail & Related papers  (2024-10-03T22:29:47Z)
• From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models [56.9134620424985]
  Cross-modal reasoning (CMR) is increasingly recognized as a crucial capability in the progression toward more sophisticated artificial intelligence systems. The recent trend of deploying Large Language Models (LLMs) to tackle CMR tasks has marked a new mainstream of approaches for enhancing their effectiveness. This survey offers a nuanced exposition of current methodologies applied in CMR using LLMs, classifying these into a detailed three-tiered taxonomy.
  arXiv  Detail & Related papers  (2024-09-19T02:51:54Z)
• Towards Data-Centric Automatic R&D [17.158255487686997]
  Researchers often seek the potential research directions by reading and then verifying them through experiments. The data-driven black-box deep learning method has demonstrated its effectiveness in a wide range of real-world scenarios. We propose a Real-world Data-centric automatic R&D Benchmark, namely RD2Bench.
  arXiv  Detail & Related papers  (2024-04-17T11:33:21Z)
• Diffusion Models for Reinforcement Learning: A Survey [22.670096541841325]
  Diffusion models surpass previous generative models in sample quality and training stability. Recent works have shown the advantages of diffusion models in improving reinforcement learning (RL) solutions. This survey aims to provide an overview of this emerging field and hopes to inspire new avenues of research.
  arXiv  Detail & Related papers  (2023-11-02T13:23:39Z)
• Ensemble Reinforcement Learning: A Survey [43.17635633600716]
  Reinforcement Learning (RL) has emerged as a highly effective technique for addressing various scientific and applied problems. In response, ensemble reinforcement learning (ERL), a promising approach that combines the benefits of both RL and ensemble learning (EL), has gained widespread popularity. ERL leverages multiple models or training algorithms to comprehensively explore the problem space and possesses strong generalization capabilities.
  arXiv  Detail & Related papers  (2023-03-05T09:26:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.