Paper Citation Record · LEDGER

Self-Rewarding Vision-Language Model via Reasoning Decomposition

As of 4 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 41 inbound Pith citation observations for arXiv:2508.19652.

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

pith.paper-citation-record.v1
2508.19652 v2

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T21:03:31.606674Z

measured 71 of 71 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 41 of 41 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T18:53:02.707977Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T12:15:01.137692Z

Reference resolution

30 of 30 outbound references displayed

verified exact12
verified fuzzy1
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch17

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 293fc308-5472-4b24-a02f-8d6ba918037d · outbound

This paper cites Qwen2.5-VL Technical Report.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Qwen2.5-VL Technical Report

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.854009Z

Source-reported events for the cited work

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

Observation a0f187c4-8a2f-4b11-acc3-86415fc8e676 · outbound

This paper cites Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.894430Z

Source-reported events for the cited work

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

Observation 27f72ccf-f6e7-47f0-8be2-cb46e75ae1dd · outbound

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

Self-Rewarding Vision-Language Model via Reasoning Decomposition Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-18T21:06:50.842818Z

Source-reported events for the cited work

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

Observation ff9d0d59-9f98-4a59-a587-6a834c107b71 · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

Self-Rewarding Vision-Language Model via Reasoning Decomposition InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.859408Z

Source-reported events for the cited work

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

Observation e1a50a99-75c1-4344-9b2e-db4716f94233 · outbound

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

Self-Rewarding Vision-Language Model via Reasoning Decomposition DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-18T21:06:50.904071Z

Source-reported events for the cited work

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

Observation d009ac87-0d15-4c3b-a2ce-d4a802682aad · outbound

This paper cites GPT-4 Technical Report.

Self-Rewarding Vision-Language Model via Reasoning Decomposition GPT-4 Technical Report

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.819432Z

Source-reported events for the cited work

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

Observation f1f2f615-d4f8-4f43-a686-c92943506c4b · outbound

This paper cites Reward shaping to mitigate reward hacking in rlhf.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Reward shaping to mitigate reward hacking in rlhf

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T21:06:50.884482Z

Source-reported events for the cited work

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

Observation ef2dc4f0-e265-4679-b6d4-e2dd59127887 · outbound

This paper cites Attention-Based Reward Shaping for Sparse and Delayed Rewards.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Attention-Based Reward Shaping for Sparse and Delayed Rewards

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.924903Z

Source-reported events for the cited work

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

Observation 8d7105e9-bd1a-4901-b191-bf3c75b8f53e · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.870094Z

Source-reported events for the cited work

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

Observation cb772b72-8f4e-40bf-b00a-250d364a23e4 · outbound

This paper cites Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T21:06:50.889155Z

Source-reported events for the cited work

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

Observation b0093d23-a9f9-4116-a40b-b88bbc091e5f · outbound

This paper cites Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.909122Z

Source-reported events for the cited work

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

Observation 7ae09349-ea87-48c8-8ee1-e57bfa4b6b35 · outbound

This paper cites More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models.

Self-Rewarding Vision-Language Model via Reasoning Decomposition More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T21:06:50.807141Z

Source-reported events for the cited work

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

Observation b5311bb5-c27b-48c5-8d9b-294a3bd75f35 · outbound

This paper cites A Survey on Hallucination in Large Vision-Language Models.

Self-Rewarding Vision-Language Model via Reasoning Decomposition A Survey on Hallucination in Large Vision-Language Models

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.874660Z

Source-reported events for the cited work

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

Observation 5b704c8c-fc4a-4656-9aa9-60b8aa3f330d · outbound

This paper cites Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.849423Z

Source-reported events for the cited work

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

Observation b4282b8d-24b2-4d02-b756-5486ebf3b871 · outbound

This paper cites The Bell System Tech- nical Journal27(3), 379–423 (1948) https://doi.org/10.1002/j.1538-7305.1948.

Self-Rewarding Vision-Language Model via Reasoning Decomposition The Bell System Tech- nical Journal27(3), 379–423 (1948) https://doi.org/10.1002/j.1538-7305.1948

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T21:06:50.351996Z

Source-reported events for the cited work

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

Observation e84b70b4-5be6-47c1-8bf3-377ccab63756 · outbound

This paper cites Spurious Rewards: Rethinking Training Signals in RLVR.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Spurious Rewards: Rethinking Training Signals in RLVR

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.837840Z

Source-reported events for the cited work

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

Observation 2bc5ef9e-81fc-4775-99e2-e3b867943254 · outbound

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

Self-Rewarding Vision-Language Model via Reasoning Decomposition DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.913499Z

Source-reported events for the cited work

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

Observation 0d7a78ad-feb8-40cf-8637-6f2f438b3313 · outbound

This paper cites Language prior is not the only shortcut: A benchmark for shortcut learning in vqa.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Language prior is not the only shortcut: A benchmark for shortcut learning in vqa

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T21:11:51.929614Z

Source-reported events for the cited work

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

Observation 00c1700a-e9b8-41b0-a2e4-0874cb7e3076 · outbound

This paper cites RLSR: Reinforcement Learning from Self Reward.

Self-Rewarding Vision-Language Model via Reasoning Decomposition RLSR: Reinforcement Learning from Self Reward

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.865244Z

Source-reported events for the cited work

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

Observation 8a3bf153-0a8b-470d-b7ea-f08e298d5ef3 · outbound

This paper cites Post-Training Large Language Models via Reinforcement Learning from Self-Feedback.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Post-Training Large Language Models via Reinforcement Learning from Self-Feedback

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.793278Z

Source-reported events for the cited work

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

Observation 7d132ff0-3378-46e0-82d5-13dc69765dc4 · outbound

This paper cites Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.824810Z

Source-reported events for the cited work

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

Observation b9bf60ec-d0b4-4ef7-a010-e50bf0495250 · outbound

This paper cites VisNumBench: Evaluating Number Sense of Multimodal Large Language Models.

Self-Rewarding Vision-Language Model via Reasoning Decomposition VisNumBench: Evaluating Number Sense of Multimodal Large Language Models

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.831375Z

Source-reported events for the cited work

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

Observation 74f7f39e-8c50-4111-bd88-6f6e8c4d0c9a · outbound

This paper cites Perception-R1: Advancing multimodal reasoning capabilities of MLLMs via visual perception reward.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Perception-R1: Advancing multimodal reasoning capabilities of MLLMs via visual perception reward

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T21:06:50.780707Z

Source-reported events for the cited work

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

Observation 114e4901-c09a-4c47-a19e-8362aa4a6701 · outbound

This paper cites Are Reasoning Models More Prone to Hallucination?.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Are Reasoning Models More Prone to Hallucination?

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.899623Z

Source-reported events for the cited work

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

Observation b58b8565-ac9d-418f-baf7-a7c69adfc8d5 · outbound

This paper cites Self-Rewarding Language Models.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Self-Rewarding Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-18T21:06:50.919220Z

Source-reported events for the cited work

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

Observation 52c95987-247e-43bb-b0ff-d8df4fd4ccb4 · outbound

This paper cites MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI.

Self-Rewarding Vision-Language Model via Reasoning Decomposition MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.787426Z

Source-reported events for the cited work

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

Observation 14aebc15-4c08-429c-a69f-337bf607fea9 · outbound

This paper cites MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark.

Self-Rewarding Vision-Language Model via Reasoning Decomposition MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.800944Z

Source-reported events for the cited work

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

Observation 8ac18930-0a43-4dde-8022-f2def321c5e8 · outbound

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

Self-Rewarding Vision-Language Model via Reasoning Decomposition R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.812882Z

Source-reported events for the cited work

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

Observation ada79fa5-e828-46fa-b761-45f3a4215ebf · outbound

This paper cites Learning to Reason without External Rewards.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Learning to Reason without External Rewards

Reference 29

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T21:06:50.879153Z

Source-reported events for the cited work

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

Observation 6c929866-b6dd-492c-98de-e715d255ec40 · outbound

This paper cites Calibrated Self-Rewarding Vision Language Models.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Calibrated Self-Rewarding Vision Language Models

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:06:50.930423Z

Source-reported events for the cited work

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

Pith citing papers

Observation 2eafd2e8-7aed-48ad-a766-753d8f68af19 · inbound

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cites this paper.

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 243

Resolution: verified exact; local_arxiv, observed 2026-05-18T19:21:48.797520Z

Source-reported events for the cited work

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

Observation b36915be-0427-4923-9bf1-971eaa09ee47 · inbound

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models cites this paper.

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-04T18:53:02.707977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d84ad3ba-d1df-450b-b707-2ee2ae46435e · inbound

DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning cites this paper.

DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-21T22:35:42.650352Z

Source-reported events for the cited work

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

Observation bcd44945-aecd-4afd-8a2c-2b81dfa37b58 · inbound

DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning cites this paper.

DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-22T13:36:35.958576Z

Source-reported events for the cited work

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

Observation 2c6590ce-6977-40c4-a451-9f9dda7cdd27 · inbound

VIDEOP2R: Video Understanding from Perception to Reasoning cites this paper.

VIDEOP2R: Video Understanding from Perception to Reasoning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-17T22:25:22.650022Z

Source-reported events for the cited work

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

Observation cd83fee7-a67b-43c8-a9ed-008127e27ec1 · inbound

EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards cites this paper.

EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T21:09:23.052942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ea4dfa3-11d9-4158-9b50-b17e8074ccdc · inbound

VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs cites this paper.

VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T20:23:04.725008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d62a3ddf-6928-4790-86fb-d5dc65b530b8 · inbound

TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech cites this paper.

TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T10:10:54.216618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b94b329-7fd3-4851-b138-f5d515deb13f · inbound

HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework cites this paper.

HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T20:19:14.531269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a68ae1-201e-4c4b-aef5-0b97f88d6cca · inbound

Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection cites this paper.

Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-21T11:20:02.501807Z

Source-reported events for the cited work

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

Observation 514393f7-012e-4e33-abb1-d27bd40f88ef · inbound

SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models cites this paper.

SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-15T01:08:25.727193Z

Source-reported events for the cited work

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

Observation 632d624b-3df6-4891-b991-456f302384e8 · inbound

VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation cites this paper.

VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-13T21:18:17.211861Z

Source-reported events for the cited work

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

Observation 62c89ad5-fd68-4c0f-af40-27ecefbed93c · inbound

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges cites this paper.

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 170

Resolution: verified exact; local_arxiv, observed 2026-05-10T14:00:28.148434Z

Source-reported events for the cited work

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

Observation b2ca0511-8271-4181-8935-f98229babc5f · inbound

EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations cites this paper.

EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:25:54.882531Z

Source-reported events for the cited work

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

Observation 4608f550-acd6-40c2-ad73-24abc60bcef4 · inbound

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data cites this paper.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 44

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:02.006979Z

Source-reported events for the cited work

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

Observation 25cba037-6055-41dc-8be2-e261c579c7e2 · inbound

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks cites this paper.

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T00:14:46.441646Z

Source-reported events for the cited work

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

Observation 0b8bdd2f-9b5a-4524-a485-fd9e7bacebc3 · inbound

Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning cites this paper.

Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:46:09.475805Z

Source-reported events for the cited work

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

Observation 468708aa-c229-4320-8bd0-d3f3ad7d69ed · inbound

Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All? cites this paper.

Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All? Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T03:36:18.582096Z

Source-reported events for the cited work

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

Observation 28ba0451-294d-4223-9158-aada18d5ab5d · inbound

Reinforcing Multimodal Reasoning Against Visual Degradation cites this paper.

Reinforcing Multimodal Reasoning Against Visual Degradation Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.272467Z

Source-reported events for the cited work

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

Observation ca736119-30ee-4cae-9c82-f376cb704189 · inbound

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification cites this paper.

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:01:24.251497Z

Source-reported events for the cited work

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

Observation f74b90da-2ddc-45f2-b32c-3af7f623c520 · inbound

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning cites this paper.

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:22:50.506455Z

Source-reported events for the cited work

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

Observation 8e6cd266-c765-47e9-8415-ab40275e0e21 · inbound

Semantic-Enriched Latent Visual Reasoning cites this paper.

Semantic-Enriched Latent Visual Reasoning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-20T06:43:05.841371Z

Source-reported events for the cited work

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

Observation d0de086b-62db-40ae-92d4-842f5e7410dc · inbound

Semantic-Enriched Latent Visual Reasoning cites this paper.

Semantic-Enriched Latent Visual Reasoning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-30T18:55:00.783814Z

Source-reported events for the cited work

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

Observation a6bf4ee8-f21d-4db2-bb37-e88da72484fb · inbound

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models cites this paper.

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:28:04.551335Z

Source-reported events for the cited work

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

Observation 4362425c-f3d1-4614-8545-2e3e350b214b · inbound

RISE: Reliable Improvement in Self-Evolving Vision-Language Models cites this paper.

RISE: Reliable Improvement in Self-Evolving Vision-Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:39:40.542640Z

Source-reported events for the cited work

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

Observation 9fc96a1f-4e3c-40ab-b7ba-a66b812737d7 · inbound

RISE: Reliable Improvement in Self-Evolving Vision-Language Models cites this paper.

RISE: Reliable Improvement in Self-Evolving Vision-Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:24:57.576003Z

Source-reported events for the cited work

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

Observation b8713252-d2d9-4d04-97b3-73766edbde3a · inbound

Visual-Advantage On-Policy Distillation for Vision-Language Models cites this paper.

Visual-Advantage On-Policy Distillation for Vision-Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.889722Z

Source-reported events for the cited work

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

Observation 32aa04c6-5614-4ca7-a836-7414863dfabe · inbound

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models cites this paper.

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:21:12.876596Z

Source-reported events for the cited work

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

Observation 7506bc9c-35d5-4bff-82ab-9a4724f08313 · inbound

Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information cites this paper.

Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:43:25.856065Z

Source-reported events for the cited work

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

Observation 03f0b52c-3524-409b-8772-9488da3ff4d8 · inbound

Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning cites this paper.

Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-29T08:33:15.656607Z

Source-reported events for the cited work

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

Observation 44e5e864-636f-4cb6-aac4-f912c2b5abe2 · inbound

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding cites this paper.

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T19:32:34.996398Z

Source-reported events for the cited work

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

Observation dd3849ca-ca49-4b81-ac7e-096a3b9bdfd2 · inbound

Scaling Participation in Modular AI Systems cites this paper.

Scaling Participation in Modular AI Systems Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 119

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T18:57:16.640238Z

Source-reported events for the cited work

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

Observation 1afc69ce-5bca-4bf7-88dd-56d96514fbef · inbound

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization cites this paper.

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 284

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:37:30.255619Z

Source-reported events for the cited work

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

Observation 7b7ec798-908f-4efb-a064-20eabcfc5268 · inbound

Improving Reasoning in Vision-Language Models via Perception Verified Self-Training cites this paper.

Improving Reasoning in Vision-Language Models via Perception Verified Self-Training Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:39.626458Z

Source-reported events for the cited work

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

Observation eb47cb2f-387e-4298-b916-725573a4bb5c · inbound

Personalizing MLLMs via Reinforced Multimodal Reference Game cites this paper.

Personalizing MLLMs via Reinforced Multimodal Reference Game Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T12:44:40.065540Z

Source-reported events for the cited work

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

Observation 3c179be6-3bc0-407a-a340-25139bc23a3f · inbound

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning cites this paper.

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 51

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T10:15:45.188616Z

Source-reported events for the cited work

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

Observation a7aa0d15-ecfb-42d8-b703-5f3bd601bbc6 · inbound

LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression cites this paper.

LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T16:58:42.352796Z

Source-reported events for the cited work

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

Observation 3158a5c5-bf95-4637-8211-a8dc6661c89f · inbound

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading cites this paper.

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T05:28:45.311405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a164a77-f953-4015-a040-5be20571ce00 · inbound

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading cites this paper.

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T15:24:58.589243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e0ded3-08e6-48e1-aa33-eefd0bad2c28 · inbound

Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation cites this paper.

Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T06:36:35.384825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f60e0dd2-6991-47d1-977c-6a66da0f9a18 · inbound

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models cites this paper.

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-31T14:46:28.736812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.