mlsanityData to 7 Oct 2026

OpenAI o1 System Card

arXiv 2412.16720 ↗First posted 21 Dec 2024cs.AIcited by 1,220

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-art performance on certain benchmarks for risks such as generating illicit advice, choosing stereotyped responses, and succumbing to known jailbreaks. Training models to incorporate a chain of thought before answering has the potential to unlock substantial benefits, while also increasing potential risks that stem from heightened intelligence. Our results underscore the need for building robust alignment methods, extensively stress-testing their efficacy, and maintaining meticulous risk management protocols. This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations.

Key facts. Cited by 1,220 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 27 of its 39 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

27 of 39 references.

References · 27

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  3. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  4. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  5. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  6. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  7. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  8. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  9. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  10. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Modelscited by 494
  11. 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 477
  12. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 457
15 more
  1. 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructionscited by 441
  2. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 429
  3. 2024A StrongREJECT for Empty Jailbreakscited by 352
  4. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  5. 2023Model evaluation for extreme riskscited by 167
  6. 2020Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claimscited by 163
  7. 2024LAB-Bench: Measuring Capabilities of Language Models for Biology Researchcited by 138
  8. 2024Evaluating Frontier Models for Dangerous Capabilitiescited by 121
  9. 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 117
  10. 2016Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussionscited by 106
  11. 2024Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Modelscited by 104
  12. 2023Deception Abilities Emerged in Large Language Modelscited by 99
  13. 2024Red-Teaming for Generative AI: Silver Bullet or Security Theater?cited by 81
  14. 2024On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Modelscited by 42
  15. 2024Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistantcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 732; 2026: 487.

1,220 papers.

Sort:

By area:

  1. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  2. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 584
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  4. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  5. 2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decompositioncited by 270
  6. 2025Inference-Time Scaling for Generalist Reward Modelingcited by 233
  7. 2025Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergycited by 204
  8. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  9. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  10. 2025Skywork Open Reasoner 1 Technical Reportcited by 161
  11. 2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!cited by 132
  12. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
38 more
  1. 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cyclescited by 122
  2. 2025Competitive Programming with Large Reasoning Modelscited by 115
  3. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  4. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  5. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspectivecited by 96
  6. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  7. 2025SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimizationcited by 87
  8. 2025Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpeningcited by 78
  9. 2025Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignmentcited by 77
  10. 2025Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judgecited by 75
  11. 2025A Survey on Latent Reasoningcited by 71
  12. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 69
  13. 2025Rank1: Test-Time Compute for Reranking in Information Retrievalcited by 68
  14. 2025Can Large Reasoning Models Self-Train?cited by 66
  15. 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agentscited by 60
  16. 2025Scaling Test-time Compute for LLM Agentscited by 59
  17. 2025RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capabilitycited by 58
  18. 2025BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoningcited by 57
  19. 2025CodeI/O: Condensing Reasoning Patterns via Code Input-Output Predictioncited by 54
  20. 2025Training a Scientific Reasoning Model for Chemistrycited by 54
  21. 2025Look-Back: Implicit Visual Re-focusing in MLLM Reasoningcited by 54
  22. 2025xVerify: Efficient Answer Verifier for Reasoning Model Evaluationscited by 53
  23. 2025FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoningcited by 53
  24. 2025Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Modelscited by 53
  25. 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learningcited by 53
  26. 2025VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledgecited by 52
  27. 2025Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimizationcited by 52
  28. 2025MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaversecited by 50
  29. 2025HumanOmniV2: From Understanding to Omni-Modal Reasoning with Contextcited by 50
  30. 2025Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Modelcited by 50
  31. 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoningcited by 49
  32. 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Datasetcited by 49
  33. 2025CoT Red-Handed: Stress Testing Chain-of-Thought Monitoringcited by 49
  34. 2025Inverse Scaling in Test-Time Computecited by 49
  35. 2025Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?cited by 48
  36. 2025Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoningcited by 48
  37. 2025GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clippingcited by 48
  38. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47

50 most cited of 1,220 All 1,220 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Don't Command, Cultivate: An Exploratory Study of System-2 Alignment
  2. 2024Deliberative Alignment: Reasoning Enables Safer Language Models
  3. 2025The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
  4. 2025AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
  5. 2025UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases
  6. 2026Internalizing Safety Understanding in Large Reasoning Models via Verification
  7. 2024System 2 thinking in OpenAI's o1-preview model: Near-perfect performance on a mathematics exam
  8. 2025H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking