Multi-Turn On-Policy Distillation with Prefix Replay | Paper Citation Record

Observation 9f443ffd-8362-49eb-bfae-22b322c58694 · outbound

This paper cites 2025 , howpublished =.

Multi-Turn On-Policy Distillation with Prefix Replay 2025 , howpublished =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:30.224369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1336d3e-9266-4ac5-bbfc-97c85160e992 · outbound

This paper cites Text Embeddings by Weakly-Supervised Contrastive Pre-training.

Multi-Turn On-Policy Distillation with Prefix Replay Text Embeddings by Weakly-Supervised Contrastive Pre-training

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:30.324022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fc72b79-7772-4889-8a16-0f2edb942c82 · outbound

This paper cites Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) , pages=.

Multi-Turn On-Policy Distillation with Prefix Replay Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) , pages=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:30.457462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baed1806-3062-421c-8bc1-68798732de3c · outbound

This paper cites Proceedings of the 2018 conference on empirical methods in natural language processing , pages=.

Multi-Turn On-Policy Distillation with Prefix Replay Proceedings of the 2018 conference on empirical methods in natural language processing , pages=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:30.574860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce64a91-a090-4428-a27f-b80b9bbbac3f · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

Multi-Turn On-Policy Distillation with Prefix Replay Transactions of the Association for Computational Linguistics , volume=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:30.695664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94141de7-8be5-4d4a-8104-c3f0c383da82 · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Measuring Mathematical Problem Solving With the MATH Dataset

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:30.860607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b86297d8-c780-4a18-bb0c-ab0c0c567073 · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Advances in Neural Information Processing Systems , volume=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:30.987077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cc13f30-31aa-462b-8616-15789eef77d7 · outbound

This paper cites Hugging Face repository , volume=.

Multi-Turn On-Policy Distillation with Prefix Replay Hugging Face repository , volume=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.063677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef84c5aa-781c-4547-860d-5637c28636db · outbound

This paper cites ReTool: Reinforcement Learning for Strategic Tool Use in LLMs.

Multi-Turn On-Policy Distillation with Prefix Replay ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.207661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24806139-c91e-4364-aebe-37f62c053b82 · outbound

This paper cites Qwen3 Technical Report.

Multi-Turn On-Policy Distillation with Prefix Replay Qwen3 Technical Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.270884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3998160e-d330-41db-a29b-35ab63f05034 · outbound

This paper cites Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL) , year=.

Multi-Turn On-Policy Distillation with Prefix Replay Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL) , year=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.392647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 676fddcd-e256-4d32-8ec9-d2ae00ecc602 · outbound

This paper cites Proceedings of the 28th International Conference on Computational Linguistics (COLING) , year=.

Multi-Turn On-Policy Distillation with Prefix Replay Proceedings of the 28th International Conference on Computational Linguistics (COLING) , year=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.522460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c0f9ccf-b2c0-442c-b62e-d55546d7bef9 · outbound

This paper cites Transactions of the Association for Computational Linguistics (TACL) , volume=.

Multi-Turn On-Policy Distillation with Prefix Replay Transactions of the Association for Computational Linguistics (TACL) , volume=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.670002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a404641d-57cb-4d5d-9a28-6cfaf69c11d0 · outbound

This paper cites Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL) , year=.

Multi-Turn On-Policy Distillation with Prefix Replay Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL) , year=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.816310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3391810-ad72-4917-9f6c-efdb4428422a · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2023 , year=.

Multi-Turn On-Policy Distillation with Prefix Replay Findings of the Association for Computational Linguistics: EMNLP 2023 , year=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:31.962421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68de4c08-32ba-451a-a155-16fbfde9defe · outbound

This paper cites Langley , title =.

Multi-Turn On-Policy Distillation with Prefix Replay Langley , title =

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:32.146843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde49871-d451-4f36-8bd2-8851a462c72f · outbound

This paper cites 2025 , eprint=.

Multi-Turn On-Policy Distillation with Prefix Replay 2025 , eprint=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:32.281887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3ecfb01-0095-44ce-ad21-fd3c930ee143 · outbound

This paper cites an unresolved cited work.

Multi-Turn On-Policy Distillation with Prefix Replay Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:32.394207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa145834-047c-4961-902a-9b90d23d035a · outbound

This paper cites an unresolved cited work.

Multi-Turn On-Policy Distillation with Prefix Replay Unresolved cited work

Reference 19

Resolution: parse uncertain; no resolver link, observed 2026-08-02T08:40:32.510605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a544614c-13b1-4c90-bd04-7d41bff4ffd3 · outbound

This paper cites an unresolved cited work.

Multi-Turn On-Policy Distillation with Prefix Replay Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:32.622142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ac50a24-4dd5-4fcb-97a7-15ba90179030 · outbound

This paper cites an unresolved cited work.

Multi-Turn On-Policy Distillation with Prefix Replay Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:32.747711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ce12b81-7b75-45fc-b22a-aba9c048ca31 · outbound

This paper cites an unresolved cited work.

Multi-Turn On-Policy Distillation with Prefix Replay Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:32.889724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17405cd1-3d3b-47b8-8f4a-1a2f7a51319b · outbound

This paper cites Newell and P.

Multi-Turn On-Policy Distillation with Prefix Replay Newell and P

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:32.978498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5688e5f-6f64-4ba4-9d60-1984f0e11167 · outbound

This paper cites The Lessons of Developing Process Reward Models in Mathematical Reasoning.

Multi-Turn On-Policy Distillation with Prefix Replay The Lessons of Developing Process Reward Models in Mathematical Reasoning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.092361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe31b435-ad89-4af7-8f3c-35f651116117 · outbound

This paper cites GitHub repository , howpublished =.

Multi-Turn On-Policy Distillation with Prefix Replay GitHub repository , howpublished =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.219015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1762d531-7f5d-4e71-beba-e3e37b041e23 · outbound

This paper cites ProcessBench: Identifying Process Errors in Mathematical Reasoning.

Multi-Turn On-Policy Distillation with Prefix Replay ProcessBench: Identifying Process Errors in Mathematical Reasoning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.379008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67f1bd67-2b41-48bc-9aaa-25bbc030fc27 · outbound

This paper cites an unresolved cited work.

Multi-Turn On-Policy Distillation with Prefix Replay Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.502772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 752cbdd9-4649-4b5e-82b5-18645ac4b389 · outbound

This paper cites Scaling Learning Algorithms Towards.

Multi-Turn On-Policy Distillation with Prefix Replay Scaling Learning Algorithms Towards

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.598903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a6ea6c5-23bb-4b5c-bc83-bc02b64b8147 · outbound

This paper cites and Osindero, Simon and Teh, Yee Whye , journal =.

Multi-Turn On-Policy Distillation with Prefix Replay and Osindero, Simon and Teh, Yee Whye , journal =

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.758155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2795fa85-3430-48d4-b071-b3f454479979 · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Advances in Neural Information Processing Systems , volume=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.857352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7fa51f1-e716-4864-af9b-10dd0af16192 · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Advances in Neural Information Processing Systems , volume=

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:33.969923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9493bcf-bb4b-4c58-91b9-018ed6a6aabe · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Advances in Neural Information Processing Systems , volume=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:34.175817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2302034-396f-4799-9db9-60a4e84d5d7c · outbound

This paper cites Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning.

Multi-Turn On-Policy Distillation with Prefix Replay Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:34.285961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24b67dc4-17e7-4270-8a97-7b57822cb507 · outbound

This paper cites Generating Sequences by Learning to Self-Correct.

Multi-Turn On-Policy Distillation with Prefix Replay Generating Sequences by Learning to Self-Correct

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:34.391896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49439340-2569-4632-95ad-47fb2e9ae9a0 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Multi-Turn On-Policy Distillation with Prefix Replay Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:34.589724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7b4aa52-d7cf-430f-bdad-2f7118defa76 · outbound

This paper cites Recursive Introspection: Teaching Language Model Agents How to Self-Improve.

Multi-Turn On-Policy Distillation with Prefix Replay Recursive Introspection: Teaching Language Model Agents How to Self-Improve

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:34.748668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c81f251-c07b-4059-a2c3-79fcf80c5546 · outbound

This paper cites RRM: Robust Reward Model Training Mitigates Reward Hacking.

Multi-Turn On-Policy Distillation with Prefix Replay RRM: Robust Reward Model Training Mitigates Reward Hacking

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:34.864629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e4255ad-0064-422d-bb92-ed138bd982b2 · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

Multi-Turn On-Policy Distillation with Prefix Replay Training Language Models to Self-Correct via Reinforcement Learning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:35.009644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b300545e-6bc3-4a35-b8d3-9a1585203b2e · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:35.127508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09af1700-6f18-4f2f-ad7e-09b2672d4da5 · outbound

This paper cites Large Language Models Cannot Self-Correct Reasoning Yet.

Multi-Turn On-Policy Distillation with Prefix Replay Large Language Models Cannot Self-Correct Reasoning Yet

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:35.247088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b049245-6f1f-4954-a740-096908245922 · outbound

This paper cites Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization.

Multi-Turn On-Policy Distillation with Prefix Replay Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:35.403262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 337bc30f-ea88-46cc-851c-97563e60a527 · outbound

This paper cites 2016 , publisher=.

Multi-Turn On-Policy Distillation with Prefix Replay 2016 , publisher=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:35.548203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9477601-761a-464d-ba86-7f81ed5390dd · outbound

This paper cites Disentangling Length from Quality in Direct Preference Optimization.

Multi-Turn On-Policy Distillation with Prefix Replay Disentangling Length from Quality in Direct Preference Optimization

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:35.672115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45b25298-d644-4be9-a4e3-e3cd9ab28394 · outbound

This paper cites Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level.

Multi-Turn On-Policy Distillation with Prefix Replay Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:35.809095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15e17f8c-3d1d-4117-a752-b61ea7913795 · outbound

This paper cites Teaching Large Language Models to Reason with Reinforcement Learning.

Multi-Turn On-Policy Distillation with Prefix Replay Teaching Large Language Models to Reason with Reinforcement Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:36.004785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3636e34-c2e4-4ae9-88f7-2d8b3818795f · outbound

This paper cites Hashimoto , title =.

Multi-Turn On-Policy Distillation with Prefix Replay Hashimoto , title =

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:36.184768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43ad6cec-431b-48e7-a216-abfaa752c32c · outbound

This paper cites 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year=.

Multi-Turn On-Policy Distillation with Prefix Replay 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:36.356815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a86c0ce-2077-42e8-9bfc-5fe801ea1dec · outbound

This paper cites Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning.

Multi-Turn On-Policy Distillation with Prefix Replay Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:36.488598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d4d236d-1d70-41a1-be45-83fe3dc9b27d · outbound

This paper cites Know What You Don't Know: Unanswerable Questions for SQuAD.

Multi-Turn On-Policy Distillation with Prefix Replay Know What You Don't Know: Unanswerable Questions for SQuAD

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:36.627944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38ca4a2a-9194-4b5e-b5fd-21168d18833b · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Advances in Neural Information Processing Systems , volume=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:36.784779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af13d23a-4ffe-4f47-aded-4a9c6e2c9efd · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay International Conference on Machine Learning , pages=

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:36.911975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1836fa-823a-4bf7-b867-5974bfa74b56 · outbound

This paper cites 2024 , publisher =.

Multi-Turn On-Policy Distillation with Prefix Replay 2024 , publisher =

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.091342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f3c4dd8-ab74-45ef-b9a4-2c089d436537 · outbound

This paper cites ACM Transactions on Information Systems (TOIS) , volume=.

Multi-Turn On-Policy Distillation with Prefix Replay ACM Transactions on Information Systems (TOIS) , volume=

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.204832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ea71156-63e4-4bb1-bd8a-be90a8fbe852 · outbound

This paper cites doi:10.57967/hf/0513 , publisher =.

Multi-Turn On-Policy Distillation with Prefix Replay doi:10.57967/hf/0513 , publisher =

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.285743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79dd8db8-7b58-4a8b-b936-fc16176c280b · outbound

This paper cites Generative Verifiers: Reward Modeling as Next-Token Prediction.

Multi-Turn On-Policy Distillation with Prefix Replay Generative Verifiers: Reward Modeling as Next-Token Prediction

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.369447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cde80cf6-ed03-41cb-a4c6-1dded28bf69c · outbound

This paper cites Generative Reward Models.

Multi-Turn On-Policy Distillation with Prefix Replay Generative Reward Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.485022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42f096b6-45c0-42cb-8ad9-9578d5e75310 · outbound

This paper cites WARM: On the Benefits of Weight Averaged Reward Models.

Multi-Turn On-Policy Distillation with Prefix Replay WARM: On the Benefits of Weight Averaged Reward Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.580679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06d6db6a-3d7b-41b0-ab22-7d0822e031e6 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

Multi-Turn On-Policy Distillation with Prefix Replay Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.766104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1771369-4264-4d3c-9503-6f2f51d0efeb · outbound

This paper cites DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving.

Multi-Turn On-Policy Distillation with Prefix Replay DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:37.931798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7d425d7-542b-4f87-8f9f-41bd278ad717 · outbound

This paper cites BOND: Aligning LLMs with Best-of-N Distillation.

Multi-Turn On-Policy Distillation with Prefix Replay BOND: Aligning LLMs with Best-of-N Distillation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.041034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ced94b72-b359-4ad9-b517-b3e03c37d5db · outbound

This paper cites 2023 , eprint=.

Multi-Turn On-Policy Distillation with Prefix Replay 2023 , eprint=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.173978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768ec640-82d1-4148-9f71-238efeaac97c · outbound

This paper cites ODIN: Disentangled Reward Mitigates Hacking in RLHF.

Multi-Turn On-Policy Distillation with Prefix Replay ODIN: Disentangled Reward Mitigates Hacking in RLHF

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.315887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed92659c-72d6-4e18-963b-ab19742f152e · outbound

This paper cites The Llama 3 Herd of Models.

Multi-Turn On-Policy Distillation with Prefix Replay The Llama 3 Herd of Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.483807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc1f96a0-d5b4-447c-bfa8-bc4840830c6a · outbound

This paper cites 2023 , publisher=.

Multi-Turn On-Policy Distillation with Prefix Replay 2023 , publisher=

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.588624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22d5c9f1-4e25-49d2-8275-3fb8638b6810 · outbound

This paper cites 2024 , journal =.

Multi-Turn On-Policy Distillation with Prefix Replay 2024 , journal =

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.643258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3902999d-d6ef-4a8d-8d30-d40e98904309 · outbound

This paper cites LIMA: Less Is More for Alignment.

Multi-Turn On-Policy Distillation with Prefix Replay LIMA: Less Is More for Alignment

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.769023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88a6371e-ac61-4295-bbac-8c2669572b83 · outbound

This paper cites ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving.

Multi-Turn On-Policy Distillation with Prefix Replay ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:38.941759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 350e3b83-e95c-497e-96fa-f4c9f3db9a24 · outbound

This paper cites Advancing LLM Reasoning Generalists with Preference Trees.

Multi-Turn On-Policy Distillation with Prefix Replay Advancing LLM Reasoning Generalists with Preference Trees

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.023948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ed1519e-8eb9-481f-995a-7df541fbaee7 · outbound

This paper cites WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct.

Multi-Turn On-Policy Distillation with Prefix Replay WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.153039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 511bdc20-4e3c-465d-951f-fbe531153738 · outbound

This paper cites Iterative Reasoning Preference Optimization.

Multi-Turn On-Policy Distillation with Prefix Replay Iterative Reasoning Preference Optimization

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.278322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8458bb9-1226-4e19-842e-bb86044fa609 · outbound

This paper cites Let's Verify Step by Step.

Multi-Turn On-Policy Distillation with Prefix Replay Let's Verify Step by Step

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.434503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21481048-a15e-45ca-a546-1ff1ed5e919a · outbound

This paper cites MAmmoTH2: Scaling Instructions from the Web.

Multi-Turn On-Policy Distillation with Prefix Replay MAmmoTH2: Scaling Instructions from the Web

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.565899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 053ca9e2-88b8-4a03-8e0f-f300343c83cb · outbound

This paper cites REBEL: Reinforcement Learning via Regressing Relative Rewards.

Multi-Turn On-Policy Distillation with Prefix Replay REBEL: Reinforcement Learning via Regressing Relative Rewards

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.691665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 611ae85f-0e67-41c6-b984-776c7bf72877 · outbound

This paper cites Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning.

Multi-Turn On-Policy Distillation with Prefix Replay Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.787640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bec1b78-d10d-4bae-a9da-fd714f79ffbc · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Advances in Neural Information Processing Systems , volume=

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.909147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9acd4b2-4ebd-42bf-90a9-62837c84ed50 · outbound

This paper cites Step-level Value Preference Optimization for Mathematical Reasoning.

Multi-Turn On-Policy Distillation with Prefix Replay Step-level Value Preference Optimization for Mathematical Reasoning

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:39.974766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad0225b5-6ede-4c58-8fe0-b39213941d98 · outbound

This paper cites nature , volume=.

Multi-Turn On-Policy Distillation with Prefix Replay nature , volume=

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.055037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c34ea7d-e742-47ae-855b-9943f89da350 · outbound

This paper cites Playing Atari with Deep Reinforcement Learning.

Multi-Turn On-Policy Distillation with Prefix Replay Playing Atari with Deep Reinforcement Learning

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.132166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f322826-12d6-45ff-ba02-ecde46fa59be · outbound

This paper cites ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent.

Multi-Turn On-Policy Distillation with Prefix Replay ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.326974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e708e9c-c64e-4a44-9328-82b071028f5d · outbound

This paper cites OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset.

Multi-Turn On-Policy Distillation with Prefix Replay OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.446065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57f4433b-5429-4247-b0f5-941d4c3dde53 · outbound

This paper cites OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data.

Multi-Turn On-Policy Distillation with Prefix Replay OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.504438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b9b7728-032c-4f5a-808e-391398aebdce · outbound

This paper cites Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF.

Multi-Turn On-Policy Distillation with Prefix Replay Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.571083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72982cdf-9a09-4958-a459-8667fbca858e · outbound

This paper cites Connection Science , volume=.

Multi-Turn On-Policy Distillation with Prefix Replay Connection Science , volume=

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.667991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8286283c-0397-4dbe-83b8-de7a5c2c8f27 · outbound

This paper cites 2010 , publisher=.

Multi-Turn On-Policy Distillation with Prefix Replay 2010 , publisher=

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.706168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 973cf8ba-f9c7-4386-a43c-032f5b5074b8 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Multi-Turn On-Policy Distillation with Prefix Replay Training Verifiers to Solve Math Word Problems

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.786290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4134c048-ba08-401b-99fa-8c8a51f261df · outbound

This paper cites 2023 , eprint=.

Multi-Turn On-Policy Distillation with Prefix Replay 2023 , eprint=

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.885199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation febdbadf-647c-400e-bf99-eb058a8397f6 · outbound

This paper cites From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function.

Multi-Turn On-Policy Distillation with Prefix Replay From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:40.977636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 779f7c7f-44bf-413e-bb64-6a5a6ac6338b · outbound

This paper cites Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer.

Multi-Turn On-Policy Distillation with Prefix Replay Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:41.047599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 910aa229-e412-462f-b930-696349ee7d06 · outbound

This paper cites LiPO: Listwise Preference Optimization through Learning-to-Rank.

Multi-Turn On-Policy Distillation with Prefix Replay LiPO: Listwise Preference Optimization through Learning-to-Rank

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:41.165786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab88c21d-49a8-4d9f-a7dc-eb3da9c9903d · outbound

This paper cites Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study.

Multi-Turn On-Policy Distillation with Prefix Replay Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:41.352028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 942f357b-7f09-40e8-a06f-eb05d914a8f9 · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

Multi-Turn On-Policy Distillation with Prefix Replay Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:41.531173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcfab427-7345-4fdc-88e9-a53c74b1df81 · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

Multi-Turn On-Policy Distillation with Prefix Replay Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:41.705346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 594a8fd3-7461-4573-91c8-b2fdff369f9e · outbound

This paper cites Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing.

Multi-Turn On-Policy Distillation with Prefix Replay Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:41.861888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0191aac-f91f-4460-b458-110a9358eb47 · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay European conference on machine learning , pages=

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.030702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c55cb8ae-dc47-45c7-9e27-fe2c1bb069fc · outbound

This paper cites Self-Consistency Preference Optimization.

Multi-Turn On-Policy Distillation with Prefix Replay Self-Consistency Preference Optimization

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.168233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52949c34-af80-4431-a8f7-2a010ee7a163 · outbound

This paper cites 2019 , publisher=.

Multi-Turn On-Policy Distillation with Prefix Replay 2019 , publisher=

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.312787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85614d0d-d12e-484e-976e-8ffddea0d4f4 · outbound

This paper cites Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs.

Multi-Turn On-Policy Distillation with Prefix Replay Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.479453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b851126-94ad-4101-a683-bfb82f6e21df · outbound

This paper cites Machine learning , volume=.

Multi-Turn On-Policy Distillation with Prefix Replay Machine learning , volume=

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.599605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e66fc51d-fff0-4293-9736-cf39e2ae36c2 · outbound

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

Multi-Turn On-Policy Distillation with Prefix Replay Advances in neural information processing systems , volume=

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.741707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06ae92ae-f1ae-40d8-b836-5f97188dcad0 · outbound

This paper cites Orca-Math: Unlocking the potential of SLMs in Grade School Math.

Multi-Turn On-Policy Distillation with Prefix Replay Orca-Math: Unlocking the potential of SLMs in Grade School Math

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.872339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers