Paper Citation Record · LEDGER

Improving RL Exploration for LLM Reasoning through Retrospective Replay

As of 17 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 6 inbound Pith citation observations for arXiv:2504.14363.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.14363 v2

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:53:29.001062Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:30:38.055667Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T07:59:40.189087Z

Reference resolution

56 of 56 outbound references displayed

verified exact1
verified fuzzy9
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 888524d1-e700-4d13-b272-6e7915a7e389 · outbound

This paper cites IEEE Signal Processing Magazine 34(6), 26–38 (2017).

Improving RL Exploration for LLM Reasoning through Retrospective Replay IEEE Signal Processing Magazine 34(6), 26–38 (2017)

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.505944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dae19bd0-8887-42d9-9b17-6e1071ebc1e6 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.575439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c90a7971-3e79-4e58-bc1b-850676693ab8 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.666657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c39bf08-9c78-4d61-9ebe-bcffa6d48bb5 · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

Improving RL Exploration for LLM Reasoning through Retrospective Replay DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.671172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d20b8933-9a52-46b1-bfc6-e781c9329f0a · outbound

This paper cites DocFusion: A Unified Framework for Document Parsing Tasks.

Improving RL Exploration for LLM Reasoning through Retrospective Replay DocFusion: A Unified Framework for Document Parsing Tasks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.675801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42bc350b-17e5-423b-92a7-b384c0860eac · outbound

This paper cites PanGu-Coder: Program Synthesis with Function-Level Language Modeling.

Improving RL Exploration for LLM Reasoning through Retrospective Replay PanGu-Coder: Program Synthesis with Function-Level Language Modeling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.679663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad4659b5-0974-46d4-a975-452382807278 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.684280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65229ffc-8d53-46e3-b205-549ceff1b21c · outbound

This paper cites In: 2008 Interna- tional Conference on Computational Intelligence for Modelling Control Automa- tion.

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: 2008 Interna- tional Conference on Computational Intelligence for Modelling Control Automa- tion

Reference 8

Resolution: verified exact; doi, observed 2026-08-16T11:53:29.036959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8b9976a4-4f52-4bd9-aa9d-cf85a28bd283 · outbound

This paper cites Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.692181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00bda77-aa71-440a-8c60-b776ea5265cf · outbound

This paper cites arXiv preprint arXiv:2407.06153 (2024).

Improving RL Exploration for LLM Reasoning through Retrospective Replay arXiv preprint arXiv:2407.06153 (2024)

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.696732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae96fd29-0008-44bd-beab-b6cc578ff7bf · outbound

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

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:30.299883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ce400777-20f3-462d-ac3f-b7f3fcd0fb7a · outbound

This paper cites MetaRM: Shifted Distributions Alignment via Meta-Learning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay MetaRM: Shifted Distributions Alignment via Meta-Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.844350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03c2a41e-5bc4-4e4c-a7df-49adf5076bd3 · outbound

This paper cites Towards Understanding the Capability of Large Language Models on Code Clone Detection: A Survey.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Towards Understanding the Capability of Large Language Models on Code Clone Detection: A Survey

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.946663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c00eeada-e0ed-49f8-86fe-a6ec1ce69bcc · outbound

This paper cites arXiv preprint arXiv:2506.02672 (2025).

Improving RL Exploration for LLM Reasoning through Retrospective Replay arXiv preprint arXiv:2506.02672 (2025)

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.950609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ded2841-43b0-4cf3-9a7e-c520a900f59e · outbound

This paper cites In: Proceedings of the 62nd Annual Meeting of the AssociationforComputationalLinguistics(Volume1:LongPapers).pp.1932–1945 (2024).

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: Proceedings of the 62nd Annual Meeting of the AssociationforComputationalLinguistics(Volume1:LongPapers).pp.1932–1945 (2024)

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:30.288728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a4f13fcd-9947-40fd-92d0-73e41fcf66b6 · outbound

This paper cites Nature590, 580 – 586 (2020),https://api.semanticscholar.org/ CorpusID:216552951.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Nature590, 580 – 586 (2020),https://api.semanticscholar.org/ CorpusID:216552951

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:30.276945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 265801ab-340f-4118-a497-9cccdf90e407 · outbound

This paper cites In: Proceedings of the 41st International Conference on Machine Learning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: Proceedings of the 41st International Conference on Machine Learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:30.231147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b5a32ec2-5821-47b7-bbf0-a158e84ef373 · outbound

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

Improving RL Exploration for LLM Reasoning through Retrospective Replay DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.965567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eefee861-05aa-4a28-b84a-77bf10127813 · outbound

This paper cites an unresolved cited work.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:53:30.130543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 48a7c01a-d34b-4642-a506-bddcf65291cd · outbound

This paper cites In: Vanschoren, J., Yeung, S.

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: Vanschoren, J., Yeung, S

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:30.118878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7b9dcbfb-6158-4163-9e86-7b9800b51638 · outbound

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

Improving RL Exploration for LLM Reasoning through Retrospective Replay Measuring Mathematical Problem Solving With the MATH Dataset

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:27.977900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9055ac67-6aae-419c-95a0-8be5bed2262c · outbound

This paper cites Towards Reasoning in Large Language Models: A Survey.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Towards Reasoning in Large Language Models: A Survey

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.013293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2d2248-5edb-4f01-a135-7b470cc0818d · outbound

This paper cites RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoning

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-08-16T11:53:29.552762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2e2a4f09-b6db-4598-92c3-e9807baa9d1a · outbound

This paper cites Understanding the Effects of RLHF on LLM Generalisation and Diversity.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Understanding the Effects of RLHF on LLM Generalisation and Diversity

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.162206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a5fd15-d033-42ca-bac4-4b1d4b32e08d · outbound

This paper cites LLM Post-Training: A Deep Dive into Reasoning Large Language Models.

Improving RL Exploration for LLM Reasoning through Retrospective Replay LLM Post-Training: A Deep Dive into Reasoning Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.167820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9c4d114-ae70-4143-b99d-e46c18016fa9 · outbound

This paper cites Information Fusion85, 1–22 (2022).

Improving RL Exploration for LLM Reasoning through Retrospective Replay Information Fusion85, 1–22 (2022)

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.174446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1896f1dd-c6fb-48f3-b105-f6967430cbcd · outbound

This paper cites StarCoder: may the source be with you!.

Improving RL Exploration for LLM Reasoning through Retrospective Replay StarCoder: may the source be with you!

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.180369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f60984d5-12cf-40a0-889c-d2d0327c1bd5 · outbound

This paper cites Deep Reinforcement Learning: An Overview.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Deep Reinforcement Learning: An Overview

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.185715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d67fe6a5-165f-4abe-981a-cdc3bc643bc2 · outbound

This paper cites RLTF: Reinforcement Learning from Unit Test Feedback.

Improving RL Exploration for LLM Reasoning through Retrospective Replay RLTF: Reinforcement Learning from Unit Test Feedback

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.190874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b834e9ad-e8c2-4d10-8381-da9a0ba90d6f · outbound

This paper cites WizardCoder: Empowering Code Large Language Models with Evol-Instruct.

Improving RL Exploration for LLM Reasoning through Retrospective Replay WizardCoder: Empowering Code Large Language Models with Evol-Instruct

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.195335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4196ed8a-44ca-45b0-8c1b-b0e3c47716de · outbound

This paper cites Brief analysis of DeepSeek R1 and its implications for Generative AI.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Brief analysis of DeepSeek R1 and its implications for Generative AI

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.200209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec987063-8bc8-4f1c-8f08-1107e78c04e4 · outbound

This paper cites In: 2018 IEEE Inter- national Conference on Robotics and Automation (ICRA).

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: 2018 IEEE Inter- national Conference on Robotics and Automation (ICRA)

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.258352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b74eb59b-54e3-4ada-ae5b-0b7b012fce14 · outbound

This paper cites arXiv preprint arXiv:2407.11511 (2024).

Improving RL Exploration for LLM Reasoning through Retrospective Replay arXiv preprint arXiv:2407.11511 (2024)

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.394078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de719de5-add6-4a7a-aa2d-16575cc7cd27 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Code Llama: Open Foundation Models for Code

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.457662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98c32d55-ab36-466a-a87f-bc3f7c533e1b · outbound

This paper cites Prioritized Experience Replay.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Prioritized Experience Replay

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.462546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 667eed7b-7bc1-4c79-9e4e-437d47d7f5e1 · outbound

This paper cites High-Dimensional Continuous Control Using Generalized Advantage Estimation.

Improving RL Exploration for LLM Reasoning through Retrospective Replay High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.512230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52cc8e12-af0e-4e6a-b088-e953c55ea7b2 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Proximal Policy Optimization Algorithms

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.596337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db5262c-478d-4508-abde-356ab74bef36 · outbound

This paper cites 5-thinking: Advancing superb reasoning models with reinforcement learning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay 5-thinking: Advancing superb reasoning models with reinforcement learning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.600249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4bc0226-3566-42ed-aba4-52742dfa2fda · outbound

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

Improving RL Exploration for LLM Reasoning through Retrospective Replay DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.603999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f232fc04-9978-43c8-8f7e-0226eb9bcb16 · outbound

This paper cites In: The 2023 Conference on Empirical Methods in Natural Language Processing.

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: The 2023 Conference on Empirical Methods in Natural Language Processing

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:30.101836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dfe5a085-9bf6-49bb-bcf9-4e0876a6106a · outbound

This paper cites Execution-based Code Generation using Deep Reinforcement Learning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Execution-based Code Generation using Deep Reinforcement Learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.614182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85e0fc10-7300-46e5-98b4-581cc48cf3a4 · outbound

This paper cites Advances in neural informa- tion processing systems12 (1999).

Improving RL Exploration for LLM Reasoning through Retrospective Replay Advances in neural informa- tion processing systems12 (1999)

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:30.047980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 562cef5c-f270-45ac-8046-207313ef9b73 · outbound

This paper cites Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.697223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32e0b9d7-d87f-4c01-975a-4981ca8b7e02 · outbound

This paper cites an unresolved cited work.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:53:29.901092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 32f7067e-076a-4510-b437-f9e204aa0d67 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.707518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a8e414d-0b82-4ddc-a9a5-3eaa050741c2 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Solving math word problems with process- and outcome-based feedback

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.711624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a10ab00-4e0a-4284-89eb-e8ac65cf2a98 · outbound

This paper cites Secrets of RLHF in Large Language Models Part II: Reward Modeling.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Secrets of RLHF in Large Language Models Part II: Reward Modeling

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.737965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61e3575d-57e1-43c4-ac9a-d246f320caf0 · outbound

This paper cites Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.847092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28577e6f-3437-4add-90e9-300765c13701 · outbound

This paper cites Machine learning8, 229–256 (1992).

Improving RL Exploration for LLM Reasoning through Retrospective Replay Machine learning8, 229–256 (1992)

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.851183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4fcf402-90c7-4a45-a758-3bc594580228 · outbound

This paper cites Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.855634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a571a8ea-e785-4453-ad81-2414c8c6a3d3 · outbound

This paper cites In: International Conference on Machine Learning.

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: International Conference on Machine Learning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:29.883416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a016837c-4a05-42e1-b30e-e793c6fd24c5 · outbound

This paper cites Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.864222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede8af13-74e9-4136-b940-c3d979966938 · outbound

This paper cites arXiv preprint arXiv:2505.17793 (2025).

Improving RL Exploration for LLM Reasoning through Retrospective Replay arXiv preprint arXiv:2505.17793 (2025)

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.869017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455a8c2b-08a9-48e3-9529-729c736bc6d6 · outbound

This paper cites A Deeper Look at Experience Replay.

Improving RL Exploration for LLM Reasoning through Retrospective Replay A Deeper Look at Experience Replay

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.872617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bff13c8d-45e2-4636-a8c6-262d0a021569 · outbound

This paper cites an unresolved cited work.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:53:29.872604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6421c666-6154-4714-ba74-d565060ac54b · outbound

This paper cites In: NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following (2023).

Improving RL Exploration for LLM Reasoning through Retrospective Replay In: NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following (2023)

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:53:29.859319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation a57d2fe3-68d0-4906-9adc-01e65938bc09 · inbound

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning cites this paper.

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning Improving RL Exploration for LLM Reasoning through Retrospective Replay

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:38.055667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 331e8f51-bedd-44b1-8469-cd6695202c97 · inbound

A Survey of Reinforcement Learning for Large Reasoning Models cites this paper.

A Survey of Reinforcement Learning for Large Reasoning Models Improving RL Exploration for LLM Reasoning through Retrospective Replay

Reference 118

Resolution: verified exact; arxiv_id, observed 2026-05-18T00:02:25.295695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8d570112-a7fc-4c0c-84ae-491828bceca0 · inbound

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning cites this paper.

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning Improving RL Exploration for LLM Reasoning through Retrospective Replay

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:56:12.821899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0d92ba2d-2def-4264-a3d6-9daafaa5fb0a · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation Improving RL Exploration for LLM Reasoning through Retrospective Replay

Reference 266

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T20:56:13.562994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f71fc0eb-23d5-43eb-abf0-9f60c6da2b44 · inbound

Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR cites this paper.

Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR Improving RL Exploration for LLM Reasoning through Retrospective Replay

Reference 101

Resolution: verified exact; arxiv_id, observed 2026-07-02T01:36:25.167562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f3695488-aca2-48e0-b879-1b07bbbd95a5 · inbound

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning cites this paper.

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning Improving RL Exploration for LLM Reasoning through Retrospective Replay

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-04T07:59:40.190471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.