Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information | Paper Citation Record

Observation 76a670ab-125a-49ab-bcf2-60f6d7ef615a · outbound

This paper cites TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:25.027123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99017e16-c354-4bea-aba2-d2e838c5bc7e · outbound

This paper cites Proceedings of the nineteenth international conference on machine learning , pages=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Proceedings of the nineteenth international conference on machine learning , pages=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:25.211148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8705f917-7223-4f55-a128-6ad9eab14077 · outbound

This paper cites ICML , pages=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information ICML , pages=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:25.413310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61627157-aa84-4dae-a66a-b432b96878ca · outbound

This paper cites an unresolved cited work.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:25.593189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93f9204f-7363-468f-a164-9954ffa6dd87 · outbound

This paper cites Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles , year=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles , year=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:25.764992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b274825a-23f3-474c-ae78-8246a3dc99f5 · outbound

This paper cites 2024 , journal =.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information 2024 , journal =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:25.910824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a43daa9-f572-4af5-8892-15caad909072 · outbound

This paper cites Qwen2.5: A Party of Foundation Models , url =.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Qwen2.5: A Party of Foundation Models , url =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:26.110796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe26e55c-788f-49e7-b414-56eaf8a2b6c7 · outbound

This paper cites 2023 , publisher =.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information 2023 , publisher =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:26.237387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5643572d-cba5-448b-bf0a-f02b61bfcf04 · outbound

This paper cites an unresolved cited work.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:26.374603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5ac987c-45d7-4838-ace6-36278d191624 · outbound

This paper cites NeurIPS , year=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information NeurIPS , year=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:26.821313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7367ab7-f7a0-4192-bbac-2a4db28eda96 · outbound

This paper cites GRPO is Secretly a Process Reward Model.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information GRPO is Secretly a Process Reward Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:27.252303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d3459f2-de37-42f7-bf7f-244c99a16118 · outbound

This paper cites arXiv preprint arXiv:2510.02263 , year=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information arXiv preprint arXiv:2510.02263 , year=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:27.376399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e78c49e-2660-4181-98bc-872084b33d59 · outbound

This paper cites Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:27.503850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8a5b6de-1ab0-41b3-90ec-3cb6462a186e · outbound

This paper cites Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:27.855935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 187488eb-2ccf-491e-a63c-b61a49664b14 · outbound

This paper cites International Conference on Machine Learning , pages=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information International Conference on Machine Learning , pages=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:28.288722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8684b0c-36a8-467d-95c0-6630ede22555 · outbound

This paper cites Advances in neural information processing systems , volume=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Advances in neural information processing systems , volume=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:28.860846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81fd7a86-975a-4723-baaf-c577a25adda2 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:29.129869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96c3a91c-0595-4ec2-a3d4-7446c5a4d6be · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Advances in Neural Information Processing Systems , volume=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:29.921610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e2dd0e6-3e08-434e-9947-053483f120ad · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:30.683113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0b33592-04e5-4541-9343-2464ea75f564 · outbound

This paper cites The twelfth international conference on learning representations , year=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information The twelfth international conference on learning representations , year=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:30.803160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 847d2d67-8a82-4edc-95fd-9fa9ada2624a · outbound

This paper cites International conference on machine learning , pages=.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information International conference on machine learning , pages=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:30.919231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ca3c92c-467d-41f1-a650-3508eceb818a · outbound

This paper cites Problems and Projects , url =.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Problems and Projects , url =

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:31.588781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecff8e9a-7084-4922-a063-5c192f79c509 · outbound

This paper cites On-policy distillation of language models: Learning from self-generated mistakes.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information On-policy distillation of language models: Learning from self-generated mistakes

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:31.783694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 752e4cd9-36ac-4349-9f16-d28225d4274a · outbound

This paper cites Rl for reasoning by adaptively revealing rationales.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Rl for reasoning by adaptively revealing rationales

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:31.938291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b0c8ca3-0dcb-4f57-8e20-c189d09fa0e9 · outbound

This paper cites Hindsight experience replay.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Hindsight experience replay

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.110014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86a1a692-43c6-4559-b87e-27e4e2779401 · outbound

This paper cites Matharena: Evaluating llms on uncontaminated math competitions, February 2025.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Matharena: Evaluating llms on uncontaminated math competitions, February 2025

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.206324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4454bc61-3edf-4c3e-bebb-180c771a479e · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Evaluating Large Language Models Trained on Code

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.306487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7137d105-8ddd-4a1f-a3a6-c8e245cb7a38 · outbound

This paper cites Self-evolving curriculum for llm reasoning.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Self-evolving curriculum for llm reasoning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.380382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 419b9932-4c23-4d10-ab26-9d6f049cfd37 · outbound

This paper cites Off-Policy Actor-Critic.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Off-Policy Actor-Critic

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.478278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcf129b3-9172-4710-b54d-160be1d82385 · outbound

This paper cites AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.568310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95d6c613-43c4-4846-8694-4ff07d2545a9 · outbound

This paper cites Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.701608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5610a2b9-97f2-43c0-a751-1c31f3f67122 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.776683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c748f7-a37a-483c-9dcc-c030f20fa417 · outbound

This paper cites G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:32.886708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03087007-6f49-4b36-8a16-2aeaae6281b1 · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Measuring mathematical problem solving with the math dataset

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.002235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d55ebfe2-6231-45b1-b371-fc8b049906a1 · outbound

This paper cites Lo RA : Low-rank adaptation of large language models.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Lo RA : Low-rank adaptation of large language models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.124762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05672ce9-64c7-4aa3-a746-8cb9d08e8e8f · outbound

This paper cites Sample-efficient online learning in lm agents via hindsight trajectory rewriting.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Sample-efficient online learning in lm agents via hindsight trajectory rewriting

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.248959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf029e8a-32fa-4a6f-af6e-c50d37b0bcff · outbound

This paper cites Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.390704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5040be-b6de-47f0-9fa6-ba73798a1b03 · outbound

This paper cites Reinforcement Learning via Self-Distillation.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Reinforcement Learning via Self-Distillation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.512106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39bbffcd-d84d-4a37-a280-23fd6827cea0 · outbound

This paper cites OpenAI o1 System Card.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information OpenAI o1 System Card

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.573130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bee3af15-8551-43dd-89d0-104a085bbd3e · outbound

This paper cites Vcrl: Variance-based curriculum reinforcement learning for large language models.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Vcrl: Variance-based curriculum reinforcement learning for large language models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.680429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a47053d8-2de4-4222-833d-7ec867bde426 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Gonzalez, Hao Zhang, and Ion Stoica

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.776828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b558264b-4770-498c-b288-d069b5ff1e56 · outbound

This paper cites Adacurl: Adaptive curriculum reinforcement learning with invalid sample mitigation and historical revisiting.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Adacurl: Adaptive curriculum reinforcement learning with invalid sample mitigation and historical revisiting

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.849756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c8df385-a953-4309-8779-b0c3f383755d · outbound

This paper cites Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:33.943411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ae50384-9417-481b-b292-f156f396d70f · outbound

This paper cites Off-policy temporal-difference learning with function approximation.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Off-policy temporal-difference learning with function approximation

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.055058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a60edbbf-4f4d-4b4e-934e-62116143940b · outbound

This paper cites Pope: Learning to reason on hard problems via privileged on-policy exploration.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Pope: Learning to reason on hard problems via privileged on-policy exploration

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.154806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a631dee2-f408-4aa5-a223-957af15975d8 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Qwen2.5: A party of foundation models, September 2024

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.330274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bb29fe9-27b0-47a6-9c07-b36ce72614eb · outbound

This paper cites Proximal Policy Optimization Algorithms.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Proximal Policy Optimization Algorithms

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.459150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ab3a12-d993-4405-aab7-671825443b07 · outbound

This paper cites Reuse your flops: Scaling rl on hard problems by conditioning on very off-policy prefixes.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Reuse your flops: Scaling rl on hard problems by conditioning on very off-policy prefixes

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.538083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 612771ae-c2fb-4ddf-89c9-2d035ecfaa18 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.607496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 375c48a9-cd49-42aa-955b-46bf68ffb8e9 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information HybridFlow: A Flexible and Efficient RLHF Framework

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.702372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8601a47d-6b23-4ca9-8ba9-1fc876d16795 · outbound

This paper cites Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.843879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1abed22-93a8-4a9b-ad17-f379c24fafb9 · outbound

This paper cites Trial and error: Exploration-based trajectory optimization of llm agents.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Trial and error: Exploration-based trajectory optimization of llm agents

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:34.973667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f5f7ff-1ce5-4d48-948b-0c8be5d470a1 · outbound

This paper cites Gates: Self-distillation under privileged context with consensus gating.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Gates: Self-distillation under privileged context with consensus gating

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:35.136503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75c7df61-efa2-4389-9325-e52819274aed · outbound

This paper cites AIME problem set 1983--2024.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information AIME problem set 1983--2024

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:35.300797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8d44f30-1f9f-4cb2-a9ac-d71eda467f99 · outbound

This paper cites Dump: Automated distribution-level curriculum learning for rl-based llm post-training.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Dump: Automated distribution-level curriculum learning for rl-based llm post-training

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:35.433069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b78cf20-0067-4eaa-a8e2-c7b386ba9419 · outbound

This paper cites Learning to Reason under Off-Policy Guidance.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Learning to Reason under Off-Policy Guidance

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:35.562246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c985210b-79e4-4f8f-bcfc-52f65016847d · outbound

This paper cites Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:35.696337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ea2e8f1-d79f-4a16-92a5-ca54c10c1d7e · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:35.828678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 164d67d3-89e1-49e6-913c-00530ca1fb4d · outbound

This paper cites Star: Bootstrapping reasoning with reasoning.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Star: Bootstrapping reasoning with reasoning

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:35.977861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18a63bc5-dc4d-451b-8b07-b4d204c121f9 · outbound

This paper cites Exgrpo: Learning to reason from experience.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Exgrpo: Learning to reason from experience

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.041500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b0118de-0224-4485-af04-c1dad64f514f · outbound

This paper cites StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.127455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af17d960-ca6b-4a1c-9b65-28ccca6f4bf8 · outbound

This paper cites CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.252133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f33e5cc-4fe0-474a-8b59-c835c36bf40e · outbound

This paper cites On-policy rl meets off-policy experts: Harmonizing supervised fine-tuning and reinforcement learning via dynamic weighting.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information On-policy rl meets off-policy experts: Harmonizing supervised fine-tuning and reinforcement learning via dynamic weighting

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.359853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a1ecbb9-838e-406b-acd3-c244cf0f52fc · outbound

This paper cites Evaluating the Performance of Large Language Models on GAOKAO Benchmark.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Evaluating the Performance of Large Language Models on GAOKAO Benchmark

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.403464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a40d002-ff71-456a-9dc0-5938a947c162 · outbound

This paper cites Scaf-grpo: Scaffolded group relative policy optimization for enhancing llm reasoning.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Scaf-grpo: Scaffolded group relative policy optimization for enhancing llm reasoning

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.575815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4499d63a-74c1-46f9-9299-604148447797 · outbound

This paper cites BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.704591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc720a5a-df46-463f-a6d2-210078bbd77b · outbound

This paper cites Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models.

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-01T12:54:36.792201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers