mlsanityData to 7 Oct 2026

Competitive Programming with Large Reasoning Models

arXiv 2502.06807 ↗First posted 3 Feb 2025cs.LG cs.AI cs.CLcited by 115

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

We show that reinforcement learning applied to large language models (LLMs) significantly boosts performance on complex coding and reasoning tasks. Additionally, we compare two general-purpose reasoning models - OpenAI o1 and an early checkpoint of o3 - with a domain-specific system, o1-ioi, which uses hand-engineered inference strategies designed for competing in the 2024 International Olympiad in Informatics (IOI). We competed live at IOI 2024 with o1-ioi and, using hand-crafted test-time strategies, placed in the 49th percentile. Under relaxed competition constraints, o1-ioi achieved a gold medal. However, when evaluating later models such as o3, we find that o3 achieves gold without hand-crafted domain-specific strategies or relaxed constraints. Our findings show that although specialized pipelines such as o1-ioi yield solid improvements, the scaled-up, general-purpose o3 model surpasses those results without relying on hand-crafted inference heuristics. Notably, o3 achieves a gold medal at the 2024 IOI and obtains a Codeforces rating on par with elite human competitors. Overall, these results indicate that scaling general-purpose reinforcement learning, rather than relying on domain-specific techniques, offers a robust path toward state-of-the-art AI in reasoning domains, such as competitive programming.

Key facts. Cited by 115 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 6 of its 16 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

6 of 16 references.

References · 6

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2024OpenAI o1 System Cardcited by 1,220
  6. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 85; 2026: 30.

115 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2026Reinforcement Learning via Self-Distillationcited by 285
  3. 2025TTRL: Test-Time Reinforcement Learningcited by 253
  4. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learningcited by 187
  5. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  6. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  7. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  8. 2025Dream-Coder 7B: An Open Diffusion Language Model for Codecited by 81
  9. 2025Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Searchcited by 48
  10. 2025QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learningcited by 46
  11. 2025DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-trainingcited by 45
  12. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
38 more
  1. 2025LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Trainingcited by 37
  2. 2026Embarrassingly Simple Self-Distillation Improves Code Generationcited by 36
  3. 2025Z1: Efficient Test-time Scaling with Codecited by 35
  4. 2025Solving Formal Math Problems by Decomposition and Iterative Reflectioncited by 35
  5. 2025Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoningcited by 33
  6. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 32
  7. 2025VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoningcited by 32
  8. 2025Heimdall: test-time scaling on the generative verificationcited by 26
  9. 2025ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoningcited by 26
  10. 2025GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveragingcited by 25
  11. 2025SWE-Dev: Building Software Engineering Agents with Training and Inference Scalingcited by 24
  12. 2025HardTests: Synthesizing High-Quality Test Cases for LLM Codingcited by 22
  13. 2025ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generationcited by 22
  14. 2025Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Modelcited by 18
  15. 2025Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learningcited by 17
  16. 2025Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmarkcited by 16
  17. 2025HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devicescited by 15
  18. 2025QFFT, Question-Free Fine-Tuning for Adaptive Reasoningcited by 15
  19. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 14
  20. 2025SSRL: Self-Search Reinforcement Learningcited by 13
  21. 2025AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentationcited by 13
  22. 2025Thinking Out Loud: Do Reasoning Models Know When They're Right?cited by 12
  23. 2025Value-Guided Search for Efficient Chain-of-Thought Reasoningcited by 12
  24. 2025Rethinking Verification for LLM Code Generation: From Generation to Testingcited by 12
  25. 2025StepFun-Prover Preview: Let's Think and Verify Step by Stepcited by 12
  26. 2025Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Draftercited by 12
  27. 2025HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systemscited by 11
  28. 2025Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learningcited by 11
  29. 2025LegalDelta: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gaincited by 11
  30. 2025Learning to Reason from Feedback at Test-Timecited by 10
  31. 2025Modeling Earth-Scale Human-Like Societies with One Billion Agentscited by 8
  32. 2025A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gapcited by 8
  33. 2025Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Modelscited by 8
  34. 2025Investigating CoT Monitorability in Large Reasoning Modelscited by 8
  35. 2025Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalizationcited by 8
  36. 2025Diverse Inference and Verification for Advanced Reasoningcited by 6
  37. 2025Generative Evaluation of Complex Reasoning in Large Language Modelscited by 6
  38. 2025ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inferencecited by 6

50 most cited of 115 All 115 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Post-Training Language Models for Gold-Medal Performance in Coding Competitions
  2. 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
  3. 2024OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
  4. 2025Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
  5. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
  6. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
  7. 2025The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
  8. 2025LLM-ProS: Analyzing Large Language Models' Performance in Competitive Problem Solving