mlsanityData to 7 Oct 2026

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

arXiv 2501.12948 ↗First posted 22 Jan 2025cs.CL cs.AI cs.LGcited by 6,146

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning (RL), obviating the need for human-labeled reasoning trajectories. The proposed RL framework facilitates the emergent development of advanced reasoning patterns, such as self-reflection, verification, and dynamic strategy adaptation. Consequently, the trained model achieves superior performance on verifiable tasks such as mathematics, coding competitions, and STEM fields, surpassing its counterparts trained via conventional supervised learning on human demonstrations. Moreover, the emergent reasoning patterns exhibited by these large-scale models can be systematically harnessed to guide and enhance the reasoning capabilities of smaller models.

Key facts. Cited by 6,146 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 28 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

20 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2017Proximal Policy Optimization Algorithms20 Jul

Other references · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  5. 2020Scaling Laws for Neural Language Modelscited by 6,411
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  10. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  11. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  12. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
7 more
  1. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  2. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 865
  3. 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Modelscited by 694
  4. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  5. 2020CLUE: A Chinese Language Understanding Evaluation Benchmarkcited by 277
  6. 2024Are We Done with MMLU?cited by 178
  7. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generationcited by 158

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4160; 2026: 1986.

6,146 papers.

Sort:

By area:

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,276
  3. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  4. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  5. 2025Group Sequence Policy Optimizationcited by 788
  6. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
  7. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 655
  8. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  9. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  10. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 515
  11. 2025Dream 7B: Diffusion Large Language Modelscited by 515
  12. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 491
38 more
  1. 2025LIMO: Less is More for Reasoningcited by 488
  2. 2025Humanity's Last Examcited by 467
  3. 2025Video-R1: Reinforcing Video Reasoning in MLLMscited by 464
  4. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  5. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 446
  6. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 439
  7. 2025LLMs Get Lost In Multi-Turn Conversationcited by 400
  8. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 398
  9. 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attentioncited by 391
  10. 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 388
  11. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  12. 2025Kimi-VL Technical Reportcited by 381
  13. 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approachcited by 372
  14. 2025Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscationcited by 338
  15. 2025Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainscited by 328
  16. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  17. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  18. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 298
  19. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 296
  20. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  21. 2025Layer by Layer: Uncovering Hidden Representations in Language Modelscited by 293
  22. 2025OpenThoughts: Data Recipes for Reasoning Modelscited by 287
  23. 2025Memory in the Age of AI Agentscited by 285
  24. 2025Reasoning with Exploration: An Entropy Perspectivecited by 277
  25. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMscited by 276
  26. 2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decompositioncited by 270
  27. 2026Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipecited by 262
  28. 2025DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoningcited by 261
  29. 2025Small Language Models are the Future of Agentic AIcited by 254
  30. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 252
  31. 2025VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuningcited by 248
  32. 2025MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attentioncited by 248
  33. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLcited by 244
  34. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  35. 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agentscited by 240
  36. 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcementcited by 234
  37. 2025AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoningcited by 234
  38. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 226

50 most cited of 6,146 All 6,146 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
  2. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  3. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
  4. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
  5. 2025General-Reasoner: Advancing LLM Reasoning Across All Domains
  6. 2025How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study
  7. 2025On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
  8. 2025Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't