Paper Citation Record · LEDGER

Learning Self-Correction in Vision-Language Models via Rollout Augmentation

As of 9 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2602.08503.

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

pith.paper-citation-record.v1
2602.08503 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:21:13.972406Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T06:45:27.857034Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T13:56:19.149879Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 70d0a3f6-bd21-4ac1-b7cd-7906b79348f9 · outbound

This paper cites write newline.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.828338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 205c4f7f-7bd0-4aec-85c4-f305160be02d · outbound

This paper cites Claude 3.5 sonnet model card addendum, 2024.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Claude 3.5 sonnet model card addendum, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.832568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57b51591-3107-47f4-aa48-85ae14a2c6fa · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.836456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f67dda4e-51dc-4deb-8b03-fe056126c410 · outbound

This paper cites Are we on the right way for evaluating large vision-language models? Advances in Neural Information Processing Systems, 37: 0 27056--27087, 2024.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Are we on the right way for evaluating large vision-language models? Advances in Neural Information Processing Systems, 37: 0 27056--27087, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.840209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4edfbaf5-67a7-4414-a103-f4cb6245babe · outbound

This paper cites Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.843641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5600bfb2-b8fa-4f5f-94ec-feae0a016c92 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.847157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d32c93b9-8e3d-4f66-a9b7-221f9d1ef093 · outbound

This paper cites and Zhang, R.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation and Zhang, R

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.850757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29de44e6-5691-4c03-9cd4-d874e2091a90 · outbound

This paper cites Vlmevalkit: An open-source toolkit for evaluating large multi-modality models.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Vlmevalkit: An open-source toolkit for evaluating large multi-modality models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.854074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c2899e4-2dc5-4a85-9214-117d522bbe4c · outbound

This paper cites Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.857385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34583ee4-ee0c-444b-9d70-25bfed191d29 · outbound

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

Learning Self-Correction in Vision-Language Models via Rollout Augmentation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.860519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e915b1-c889-4e9b-9790-b3b84e4d5e7e · outbound

This paper cites GPT-4o System Card.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation GPT-4o System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.864335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffcab89f-e46e-4187-b1c6-ef46b7c0af0a · outbound

This paper cites OpenAI o1 System Card.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation OpenAI o1 System Card

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.867754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d022775d-2220-4123-95db-46bdbddfefa3 · outbound

This paper cites Look again, think slowly: Enhancing visual reflection in vision-language models.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Look again, think slowly: Enhancing visual reflection in vision-language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.871940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a315bf8b-9604-4635-b73d-915505ca5c78 · outbound

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

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Training Language Models to Self-Correct via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.875111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eac0620b-09e0-4fbf-aab3-ad8008beed43 · outbound

This paper cites H., Gonzalez, J.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation H., Gonzalez, J

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.878279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9fdc6b7-6594-45f7-a494-178c7ef5778a · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.881298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f5a1e8-506d-4662-aba7-03be9d80e269 · outbound

This paper cites an unresolved cited work.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.884637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42dead94-8c66-4fb5-b628-9b550f2e79cc · outbound

This paper cites Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.887624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 059a77d4-f74b-4a8b-a71f-78d97344c433 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.891083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43e7b87-370d-4494-844d-54a9bc84120c · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Self-refine: Iterative refinement with self-feedback

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.894328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42d150b9-d757-4e55-b8d5-847ca62dff35 · outbound

This paper cites L., Tan, J.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation L., Tan, J

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.897277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c85aff74-3635-4b8a-bb67-dcca7a2768bb · outbound

This paper cites Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.900352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 750a83f8-29ea-4732-b46c-a8bf25f968a5 · outbound

This paper cites an unresolved cited work.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.903784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0de85f-d0fb-4ac1-8123-c374e7e4026c · outbound

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

Learning Self-Correction in Vision-Language Models via Rollout Augmentation DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.906826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aff086c-97a1-4861-96b9-0f125780ac6a · outbound

This paper cites Srpo: Enhancing multimodal llm reasoning via reflection-aware reinforcement learning.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Srpo: Enhancing multimodal llm reasoning via reflection-aware reinforcement learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.909940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation def79938-6814-47ff-95bc-e777b88801a7 · outbound

This paper cites VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.913033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fde56f7-fc30-47f7-a5b5-25c842b4b746 · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.917664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1478b99e-35d9-45ef-b481-a9237ec9ca09 · outbound

This paper cites SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.921539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76033a86-4052-42d2-bb78-d5c307e40699 · outbound

This paper cites Charxiv: Charting gaps in realistic chart understanding in multimodal llms.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Charxiv: Charting gaps in realistic chart understanding in multimodal llms

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.924847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c065b604-b9e3-4e69-84f2-dd8ab5341b75 · outbound

This paper cites V., Zhou, D., et al.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation V., Zhou, D., et al

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.927695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f537819-a78b-4e4e-8494-e6c407fc8e08 · outbound

This paper cites MiMo-VL Technical Report.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation MiMo-VL Technical Report

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.930637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 120a71e1-6f58-4d1e-822a-b6a170ba68d8 · outbound

This paper cites Llava-cot: Let vision language models reason step-by-step.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Llava-cot: Let vision language models reason step-by-step

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.933805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3896ec2-27d8-4c99-918e-7b4aba42deeb · outbound

This paper cites Qwen3 Technical Report.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Qwen3 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.936891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6e4d58-357f-4d24-a45c-e2b88533f0d7 · outbound

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

Learning Self-Correction in Vision-Language Models via Rollout Augmentation DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.939966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaa2445b-b441-4f51-9e5b-f79ef4f19982 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.943200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66bcf109-c5c6-4e75-b892-2d5608f460bb · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.946237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda9b2f5-09e6-4d90-b771-8bf4a4e68d19 · outbound

This paper cites Evolving llms' self-refinement capability via iterative preference optimization.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Evolving llms' self-refinement capability via iterative preference optimization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.949689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 775c1e07-9e2e-440e-aed9-28be4a1a3986 · outbound

This paper cites R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.952698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f22f2d1-250d-4936-8c9a-e3f03266fc8b · outbound

This paper cites Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? In European Conference on Computer Vision, pp.\ 169--186.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? In European Conference on Computer Vision, pp.\ 169--186

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.955811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ace3ceb4-62cd-442f-888e-6f48df7e1117 · outbound

This paper cites Small language models need strong verifiers to self-correct reasoning.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Small language models need strong verifiers to self-correct reasoning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.959015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5600fd11-4511-4c33-8d85-fc507c4a1722 · outbound

This paper cites MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.961875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9308a1-b17b-4d04-9f31-13d65d4fd0f6 · outbound

This paper cites Group Sequence Policy Optimization.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Group Sequence Policy Optimization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.965141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b05f92e3-598b-4804-9a38-39866bb2bc59 · outbound

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

Learning Self-Correction in Vision-Language Models via Rollout Augmentation LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.968926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f138cb-58e0-4824-a831-82b22c490c80 · outbound

This paper cites Easyr1: An efficient, scalable, multi-modality rl training framework.

Learning Self-Correction in Vision-Language Models via Rollout Augmentation Easyr1: An efficient, scalable, multi-modality rl training framework

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T03:21:13.972406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 787af9da-b4b9-412f-96b4-ce2c6b31134d · inbound

BUS: Brain-Inspired Unsupervised Self-Reflection via Backward Prediction for Multimodal Reasoning cites this paper.

BUS: Brain-Inspired Unsupervised Self-Reflection via Backward Prediction for Multimodal Reasoning Learning Self-Correction in Vision-Language Models via Rollout Augmentation

Reference 108

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T13:56:19.151657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5090e2b1-e65a-45bb-94b1-ff5bb52dd9a7 · inbound

BUS: Brain-Inspired Unsupervised Self-Reflection via Backward Prediction for Multimodal Reasoning cites this paper.

BUS: Brain-Inspired Unsupervised Self-Reflection via Backward Prediction for Multimodal Reasoning Learning Self-Correction in Vision-Language Models via Rollout Augmentation

Reference 108

Resolution: unresolved; no resolver link, observed 2026-07-13T06:45:27.857034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.