mlsanityData to 7 Oct 2026

General-Reasoner: Advancing LLM Reasoning Across All Domains

arXiv 2505.14652 ↗First posted 20 May 2025cs.CLcited by 132

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforcement learning introduced by Deepseek-R1-Zero, enables direct RL training of base LLMs without relying on an intermediate supervised fine-tuning stage. Despite these advancements, current works for LLM reasoning mainly focus on mathematical and coding domains, largely due to data abundance and the ease of answer verification. This limits the applicability and generalization of such models to broader domains, where questions often have diverse answer representations, and data is more scarce. In this paper, we propose General-Reasoner, a novel training paradigm designed to enhance LLM reasoning capabilities across diverse domains. Our key contributions include: (1) constructing a large-scale, high-quality dataset of questions with verifiable answers curated by web crawling, covering a wide range of disciplines; and (2) developing a generative model-based answer verifier, which replaces traditional rule-based verification with the capability of chain-of-thought and context-awareness. We train a series of models and evaluate them on a wide range of datasets covering wide domains like physics, chemistry, finance, electronics etc. Our comprehensive evaluation across these 12 benchmarks (e.g. MMLU-Pro, GPQA, SuperGPQA, TheoremQA, BBEH and MATH AMC) demonstrates that General-Reasoner outperforms existing baseline methods, achieving robust and generalizable reasoning performance while maintaining superior effectiveness in mathematical reasoning tasks.

Key facts. Cited by 132 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 22 of its 30 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

22 of 30 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining12 May
  2. 2025Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning15 Apr
  3. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model31 Mar
  4. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains31 Mar
  5. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild24 Mar

Other references · 17

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  7. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  8. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  9. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  10. 2025s1: Simple test-time scalingcited by 1,311
  11. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  12. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
5 more
  1. 2025Demystifying Long Chain-of-Thought Reasoning in LLMscited by 323
  2. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 215
  3. 2023TheoremQA: A Theorem-driven Question Answering datasetcited by 189
  4. 2024MAmmoTH2: Scaling Instructions from the Webcited by 143
  5. 2025Efficient Test-Time Scaling via Self-Calibrationcited by 74

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 65; 2026: 67.

132 papers.

Sort:

By area:

  1. 2025Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainscited by 328
  2. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
  3. 2025Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergycited by 204
  4. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  5. 2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoningcited by 101
  6. 2025VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Usecited by 92
  7. 2025RLPR: Extrapolating RLVR to General Domains without Verifierscited by 83
  8. 2025SPICE: Self-Play In Corpus Environments Improves Reasoningcited by 78
  9. 2025Reinforcing General Reasoning without Verifierscited by 76
  10. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspectivecited by 75
  11. 2025In-the-Flow Agentic System Optimization for Effective Planning and Tool Usecited by 67
  12. 2025One Token to Fool LLM-as-a-Judgecited by 56
38 more
  1. 2025MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoningcited by 56
  2. 2025ExGRPO: Learning to Reason from Experiencecited by 49
  3. 2025Self-Questioning Language Modelscited by 47
  4. 2025SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agentcited by 44
  5. 2025Online Rubrics Elicitation from Pairwise Comparisonscited by 41
  6. 2025Reinforcement Pre-Trainingcited by 40
  7. 2025CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Rewardcited by 39
  8. 2025Guided Self-Evolving LLMs with Minimal Human Supervisioncited by 33
  9. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  10. 2026MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methodscited by 27
  11. 2025ICL-Router: In-Context Learned Model Representations for LLM Routingcited by 26
  12. 2025VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domainscited by 22
  13. 2025From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoningcited by 19
  14. 2025Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Densecited by 19
  15. 2025Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoningcited by 18
  16. 2026Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoningcited by 18
  17. 2025MUR: Momentum Uncertainty guided Reasoning for Large Language Modelscited by 17
  18. 2025Language Models Can Learn from Verbal Feedback Without Scalar Rewardscited by 17
  19. 2025Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learningcited by 16
  20. 2025NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learningcited by 15
  21. 2025Environment Scaling for Interactive Agentic Experience Collection: A Surveycited by 13
  22. 2025Scaling Physical Reasoning with the PHYSICS Datasetcited by 12
  23. 2025CLUE: Non-parametric Verification from Experience via Hidden-State Clusteringcited by 12
  24. 2025Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMscited by 12
  25. 2025K2-Think: A Parameter-Efficient Reasoning Systemcited by 11
  26. 2026Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Trainingcited by 11
  27. 2026GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learningcited by 10
  28. 2025Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Schedulingcited by 9
  29. 2025LaSeR: Reinforcement Learning with Last-Token Self-Rewardingcited by 9
  30. 2026Advancing General-Purpose Reasoning Models with Modular Gradient Surgerycited by 9
  31. 2025Variational Reasoning for Language Modelscited by 8
  32. 2025Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learningcited by 8
  33. 2025Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levelscited by 8
  34. 2025PretrainZero: Reinforcement Active Pretrainingcited by 8
  35. 2026Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utilitycited by 8
  36. 2025Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalizationcited by 7
  37. 2025Escaping the Verifier: Learning to Reason via Demonstrationscited by 7
  38. 2026Explainable LLM Unlearning Through Reasoningcited by 7

50 most cited of 132 All 132 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMs
  2. 2025DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training
  3. 2025Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
  4. 2025Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
  5. 2025Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  7. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
  8. 2026CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning