When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon | Paper Citation Record

Observation e6ecc6ef-d751-4055-a081-04adab472a1c · outbound

This paper cites and Ng, A.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Ng, A

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4197188a-3029-41ef-b840-94aafab0c77d · outbound

This paper cites R., Geist, M., and Bachem, O.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon R., Geist, M., and Bachem, O

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 075fac4a-e750-443b-9f34-2f1fac85b87f · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c3ea4b-bb4f-4ec1-bd36-2e919eebf1f5 · outbound

This paper cites Mitigating covariate shift in imitation learning via offline data with partial coverage.Advances in Neural Information Processing Systems, 34: 965–979, 2021.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Mitigating covariate shift in imitation learning via offline data with partial coverage.Advances in Neural Information Processing Systems, 34: 965–979, 2021

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b32e285a-b95c-423e-862c-f98e37c62af1 · outbound

This paper cites Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.680586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 430c45ed-53aa-45f7-9ee2-1b69625823ad · outbound

This paper cites and Jiang, N.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Jiang, N

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49b4608b-25d6-4b4c-90d5-f4e347799661 · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:44:21.715939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a2cb1f82-808c-4719-bfc7-532e68c6104b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.694221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0d477e39-78e9-4623-83d9-a27348479ae4 · outbound

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

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.689693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8d1f14fc-9eb1-4919-ae0a-bef84651709b · outbound

This paper cites Efficient Imitation under Misspecification.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Efficient Imitation under Misspecification

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:44:21.686151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4ad30175-9af4-4d58-9734-6591a09a9435 · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1, 2025.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Open r1: A fully open reproduction of deepseek-r1, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f2345a-3bb7-4d2d-8768-c967fa4b94c9 · outbound

This paper cites and Rakhlin, A.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Rakhlin, A

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adbc819d-0c78-460a-aaee-f658c0746e10 · outbound

This paper cites Practical contextual bandits with regression oracles.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Practical contextual bandits with regression oracles

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcc258ac-dccc-4fc0-ba6c-3bdc115970d9 · outbound

This paper cites Foundations of Reinforcement Learning and Interactive Decision Making.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Foundations of Reinforcement Learning and Interactive Decision Making

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:44:21.684171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e375f995-898d-4616-8ce7-980ff88982b7 · outbound

This paper cites J., Block, A., and Misra, D.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon J., Block, A., and Misra, D

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d44558d4-589e-4d64-bb46-56032da01c9d · outbound

This paper cites Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:44:21.676876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 514081ac-b878-47c2-963e-755dfc9be6a5 · outbound

This paper cites Importance-weighted offline learning done right.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Importance-weighted offline learning done right

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329e5e25-8a11-4114-b9ac-57280cf47c76 · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.660955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 97d1f188-33ff-4a64-82dc-e09b05ef17b1 · outbound

This paper cites The Llama 3 Herd of Models.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon The Llama 3 Herd of Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.691753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b872c7ac-445d-4098-9522-e16329086b3d · outbound

This paper cites Minillm: Knowledge distillation of large language models.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Minillm: Knowledge distillation of large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8833fb0-b182-47b4-9370-24a8a1e22b79 · outbound

This paper cites The false promise of imitating proprietary language models.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon The false promise of imitating proprietary language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bf18e55-98bd-458e-98d3-e2e489b827eb · outbound

This paper cites Skywork Open Reasoner 1 Technical Report.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Skywork Open Reasoner 1 Technical Report

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:44:21.668673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9b5002de-bb16-47d0-8f82-447d22aed129 · outbound

This paper cites Measuring massive multitask language understanding.Proceedings of the International Conference on Learning Representations (ICLR), 2021.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Measuring massive multitask language understanding.Proceedings of the International Conference on Learning Representations (ICLR), 2021

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d988d1d-fc52-4f64-964b-808eac0b58de · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Measuring Mathematical Problem Solving With the MATH Dataset

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.720735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 26ce6a87-3ecd-41bf-893f-212e74ed801a · outbound

This paper cites J., Rohatgi, D., Zhang, C., Simchowitz, M., Ash, J.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon J., Rohatgi, D., Zhang, C., Simchowitz, M., Ash, J

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2fa29c5-d07f-47bc-a639-8f563056cb2f · outbound

This paper cites D., Sun, W., Krishnamurthy, A., and Foster, D.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon D., Sun, W., Krishnamurthy, A., and Foster, D

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc7794d-b053-4f93-9638-4d82093666cd · outbound

This paper cites Teach small models to reason by curriculum distillation.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Teach small models to reason by curriculum distillation

Reference 27

Resolution: verified exact; doi, observed 2026-06-30T07:44:20.901838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6dc6b239-0651-4de7-8802-b22647781dee · outbound

This paper cites Coverage improvement and fast convergence of on-policy preference learning.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Coverage improvement and fast convergence of on-policy preference learning

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:44:21.718311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 46f206eb-ebbb-4e66-97f4-5c7b02b9da37 · outbound

This paper cites and Rush, A.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Rush, A

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88b622f4-6d1f-4306-b0af-6e1b3356c625 · outbound

This paper cites M., Ma, T., and Liang, P.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon M., Ma, T., and Liang, P

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b9c6d6a-b457-494f-83a3-274ad822b955 · outbound

This paper cites H., Gonzalez, J.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon H., Gonzalez, J

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1daa683a-9730-441d-aa12-731c07693706 · outbound

This paper cites Small models struggle to learn from strong reasoners.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Small models struggle to learn from strong reasoners

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:44:21.725590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bfb4fcdf-7b70-486b-af71-298cbce4cab2 · outbound

This paper cites Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.716774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8c68a5fc-1fa5-47c7-8da4-7aacddbfdaf6 · outbound

This paper cites DeepSeek-V3 Technical Report.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon DeepSeek-V3 Technical Report

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.728180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 071bb425-ae7c-47e7-a37b-65d0bc260cf5 · outbound

This paper cites On-policy distillation.Thinking Machines Lab: Con- nectionism.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon On-policy distillation.Thinking Machines Lab: Con- nectionism

Reference 35

Resolution: verified exact; doi, observed 2026-06-30T07:44:20.907739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9f6dfbeb-c5e1-4b47-b02a-aefa074a40f8 · outbound

This paper cites Y., Roongta, M., Cai, C., Luo, J., Zhang, T., Li, L.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Y., Roongta, M., Cai, C., Luo, J., Zhang, T., Li, L

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 535fd6ba-9f55-452c-8b69-ed3c15227e91 · outbound

This paper cites Error bounds for approximate policy iteration.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Error bounds for approximate policy iteration

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f25117d1-1e01-4517-92f0-4b015651280f · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e207bce3-a813-4af9-aaa5-593dd7bebf7d · outbound

This paper cites Tinyzero.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Tinyzero

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 372fedce-f965-4373-9074-a4318bf0b4b0 · outbound

This paper cites W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea2c163-8c6f-43f2-9a5b-d50fa6a4e6ba · outbound

This paper cites D., Ermon, S., and Finn, C.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon D., Ermon, S., and Finn, C

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01f04023-31a1-4d6c-8fd9-cdaa49f6e738 · outbound

This paper cites Toward the fundamental limits of imitation learning.Advances in Neural Information Processing Systems, 33:2914–2924, 2020.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Toward the fundamental limits of imitation learning.Advances in Neural Information Processing Systems, 33:2914–2924, 2020

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57687ae9-7134-4ddd-8b39-318901d0021d · outbound

This paper cites On the value of interaction and function approximation in imitation learning.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon On the value of interaction and function approximation in imitation learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7a9aeb8-f620-453b-a73a-2675f5a77010 · outbound

This paper cites Bridging offline reinforcement learning and imitation learning: A tale of pessimism.Advances in Neural Information Processing Systems, 34: 11702–11716, 2021.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Bridging offline reinforcement learning and imitation learning: A tale of pessimism.Advances in Neural Information Processing Systems, 34: 11702–11716, 2021

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a212c74-7aa4-494e-88e0-d435fd51322d · outbound

This paper cites Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:44:21.722568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cbad912d-9437-40b0-b862-9a8d7517e18a · outbound

This paper cites and Bagnell, D.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Bagnell, D

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a4556c6-937b-4a99-b035-2d7504350ce5 · outbound

This paper cites Reinforcement and Imitation Learning via Interactive No-Regret Learning.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Reinforcement and Imitation Learning via Interactive No-Regret Learning

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.694949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6e02cead-b9f5-404f-9506-342a0692c9f2 · outbound

This paper cites A reduction of imitation learning and structured prediction to no-regret online learning.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon A reduction of imitation learning and structured prediction to no-regret online learning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d4c68e9-8568-45fe-b51e-f274d20b9fb7 · outbound

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

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 49

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:44:21.704969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 91b6f3bb-e78c-4e41-8d34-2bd1d8aefff8 · outbound

This paper cites RL's Razor: Why Online Reinforcement Learning Forgets Less.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon RL's Razor: Why Online Reinforcement Learning Forgets Less

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.697599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 90af2d49-d326-460b-a8e5-3588fe7ae1fd · outbound

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

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon HybridFlow: A Flexible and Efficient RLHF Framework

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.731045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bc42ebcf-c246-43f2-91fa-658f0a705367 · outbound

This paper cites and Xu, Y.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Xu, Y

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 500fff68-4926-46d5-afca-510c176a127d · outbound

This paper cites an unresolved cited work.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Unresolved cited work

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:44:21.736812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dac5e4a0-5f53-42b8-b909-a0faaebf5e78 · outbound

This paper cites and Joachims, T.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Joachims, T

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 539c8a90-60c8-45ce-a0f2-35e51b47d52f · outbound

This paper cites A., Wu, S., Jiao, J., and Ramchandran, K.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon A., Wu, S., Jiao, J., and Ramchandran, K

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0f03878-046d-4363-94fa-03d3f5fac845 · outbound

This paper cites and Schapire, R.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon and Schapire, R

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8fc4515-e50b-47dc-a6ef-da31fa0dc109 · outbound

This paper cites an unresolved cited work.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4614499-a943-4cec-bbe7-863c423253f5 · outbound

This paper cites TRL: Transformers Reinforcement Learning, 2020.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon TRL: Transformers Reinforcement Learning, 2020

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe2005c-ef1b-44da-aa88-7162b875dcb3 · outbound

This paper cites Oracle-efficient pessimism: Offline policy optimization in contextual bandits.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Oracle-efficient pessimism: Offline policy optimization in contextual bandits

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5c3aa2-a3d2-4dfd-aaae-a1fe028437dd · outbound

This paper cites MiMo-V2-Flash Technical Report.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon MiMo-V2-Flash Technical Report

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.711026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f439881c-abb8-4bfa-a487-04722f306782 · outbound

This paper cites J., Krishnamurthy, A., Rosset, C., Awadallah, A.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon J., Krishnamurthy, A., Rosset, C., Awadallah, A

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cec4c83d-8ba5-45b8-b569-d375ceb5c8f1 · outbound

This paper cites Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:44:21.719763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4a6c6593-2f2a-4241-bf63-b04120034149 · outbound

This paper cites Qwen3 Technical Report.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Qwen3 Technical Report

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.702962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad3d0918-f783-4a0d-a8e2-8196820c24aa · outbound

This paper cites Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.705666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3cc4f7cc-812d-45bd-8f87-37922110c0a6 · outbound

This paper cites Black-box on-policy distillation of large language models.arXiv preprint.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Black-box on-policy distillation of large language models.arXiv preprint

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:44:20.905986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e89c053f-f5e3-4677-8fcb-b908766283f2 · outbound

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

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.713112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b7a0ec17-5518-464c-9918-2a0b2dccfa3a · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.734197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fd06f75f-e44a-4cfd-8d14-2893de821aa8 · outbound

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

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:44:20.910562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a719017c-7e4e-4dca-8e43-1d5bfa4bb9c0 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 69

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:44:21.713644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e5d8dd9d-938e-42d4-840c-c9850ca54a55 · outbound

This paper cites ζ 2 l−1X i=1 1[i̸∈ X(D)] # ≥ 1 2 E.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon ζ 2 l−1X i=1 1[i̸∈ X(D)] # ≥ 1 2 E

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d366ecbd-de05-4adf-9b12-847b66d6646a · outbound

This paper cites Warmup Supervised Fine-Tuning.To enable RL training, we first perform supervised fine-tuning on the OpenR1 dataset [11] to strengthen the model’s reasoning capabilities.

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon Warmup Supervised Fine-Tuning.To enable RL training, we first perform supervised fine-tuning on the OpenR1 dataset [11] to strengthen the model’s reasoning capabilities

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-30T07:41:39.266071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers