mlsanityData to 7 Oct 2026

GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling

arXiv 2606.04516 ↗First posted 3 Jun 2026cs.LG cs.AIcited by 1

On the map: LLM reasoning → Reinforcement learning for reasoning

also in 1 more
Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation costs, while unsupervised alternatives suffer from severe model collapse. Recent semi-supervised RLVR methods address this by using a small labeled set to guide unlabeled data, achieving a promising trade-off between training efficacy and annotation cost. However, they suffer from a severe data-efficiency bottleneck due to the reliance on coarse performance heuristics, leaving a vast majority of valuable instances underutilized. To this end, we propose GeoMin, which models global feature distributions on labeled data to decode the structural discrepancy between correct and incorrect rollouts, thereby establishing a robust prior to assess the reliability of self-reward signals and fully unleash the potential of unlabeled data. Empirically, GeoMin outperforms the strongest baselines by +4.1% and even surpasses fully supervised models with only 10% of the annotations, demonstrating remarkable data efficiency.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 28 of its 38 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

28 of 38 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning15 Dec
  2. 2025Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning10 Jun
  3. 2025Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models5 Jun
  4. 2025Can Large Reasoning Models Self-Train?27 May
  5. 2025Learning to Reason without External Rewards26 May
  6. 2025SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data25 May
  7. 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning21 May
  8. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Data6 May
  9. 2025Learning to Reason under Off-Policy Guidance21 Apr
  10. 2025Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization8 Apr
  11. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains31 Mar

Other references · 17

  1. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  3. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  5. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  6. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  7. 2019Root Mean Square Layer Normalizationcited by 1,425
  8. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  9. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  10. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  11. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  12. 2019Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learningcited by 103
5 more
  1. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  2. 2025ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanismcited by 35
  3. 2025Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Modelscited by 15
  4. 2025Post-Training Large Language Models via Reinforcement Learning from Self-Feedbackcited by 14
  5. 2025CGMatch: A Different Perspective of Semi-supervised Learningcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DE-Venus: A Data-Efficient RLVR Framework for Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
  2. 2026Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
  3. 2026How Far Can Unsupervised RLVR Scale LLM Training?
  4. 2026Boosting LLM Exploration via Weak-Model Guidance in RLVR
  5. 2026GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR
  6. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
  7. 2025RLPR: Extrapolating RLVR to General Domains without Verifiers
  8. 2025LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment