Paper Citation Record · LEDGER

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

As of 9 August 2026, this Paper Citation Record lists 91 of 91 outbound references and 10 inbound Pith citation observations for arXiv:2505.22334.

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

pith.paper-citation-record.v1
2505.22334 v2

Coverage vector

measured 91 of 91 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:13:01.038049Z

measured 101 of 101 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 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T01:47:07.116263Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T19:20:06.732932Z

Reference resolution

91 of 91 outbound references displayed

verified exact0
verified fuzzy21
unresolved70
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cf2f7f32-6e97-49ea-aaa4-86384daa567f · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start The claude 3 model family: Opus, sonnet, haiku

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:52.537010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7282e936-d0fc-4c87-98b4-c92ea2a75876 · outbound

This paper cites Qwen2.5-VL Technical Report.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:52.627521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa782b2-efae-4fe7-a425-fab274a35187 · outbound

This paper cites An augmented benchmark dataset for geometric question answering through dual parallel text encoding.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start An augmented benchmark dataset for geometric question answering through dual parallel text encoding

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:52.685659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ea13821-0f53-4f4b-8ade-72e0f46458a1 · outbound

This paper cites Sft or rl? an early investigation into training r1-like reasoning large vision-language models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Sft or rl? an early investigation into training r1-like reasoning large vision-language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:52.793186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9b8d8f3-4bab-4c2e-8cf4-ba4ff0f32a3a · outbound

This paper cites Geoqa: A geometric question answering benchmark towards multimodal numerical reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Geoqa: A geometric question answering benchmark towards multimodal numerical reasoning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:52.892662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3ba1c2c-06f5-4181-8bac-377a0ebf08fd · outbound

This paper cites R1-v: Reinforcing super generalization ability in vision-language models with less than $3.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start R1-v: Reinforcing super generalization ability in vision-language models with less than $3

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:52.971155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd47ed3-9fdb-42bd-b6ce-cd2a04bbea3b · outbound

This paper cites Sharegpt4v: Improving large multi-modal models with better captions.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Sharegpt4v: Improving large multi-modal models with better captions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.054692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6e6e4a9-3d92-4866-95c0-a526d30c03aa · outbound

This paper cites M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.142788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c35fc60-7847-4323-a846-5c23a3736f1b · outbound

This paper cites Vision-Language Models Can Self-Improve Reasoning via Reflection.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Vision-Language Models Can Self-Improve Reasoning via Reflection

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.239198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df2bc233-7654-44c7-8989-c034770064d6 · outbound

This paper cites OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.300884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e31527-5aaa-426e-b768-4588cb091ccd · outbound

This paper cites Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.376458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e83f93d-a0b6-4051-9d6d-f315e394bb53 · outbound

This paper cites Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.471122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d36db9d-6f0f-4569-8293-21758f36f9e8 · outbound

This paper cites Introducing gemini 2.0: our new ai model for the agentic era, 2024.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Introducing gemini 2.0: our new ai model for the agentic era, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.564403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42f47a43-0c55-4d9a-87f5-69e2caac04da · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.642938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f099e45b-584b-4429-90f8-7bfef4ee4b09 · outbound

This paper cites MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.708467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e8e55a2-7f5b-4e2d-82c6-7bbe078069f3 · outbound

This paper cites Infimm-webmath-40b: Advancing multimodal pre-training for enhanced mathematical reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Infimm-webmath-40b: Advancing multimodal pre-training for enhanced mathematical reasoning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.764326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7706e48-a2e3-4ff6-bf07-642cdc4169d1 · outbound

This paper cites Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.817955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffe533d3-e574-461b-a2d4-fdd83d57c5ac · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.897667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2d1fc8d-40b8-4614-9802-4c1dbbd23734 · outbound

This paper cites GPT-4o System Card.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start GPT-4o System Card

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:53.965180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35201955-b0e0-4f7c-8e2f-65c9598af8de · outbound

This paper cites OpenAI o1 System Card.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start OpenAI o1 System Card

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.061385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d7fd054-2c18-4304-8e71-800a895a9c70 · outbound

This paper cites FigureQA: An Annotated Figure Dataset for Visual Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start FigureQA: An Annotated Figure Dataset for Visual Reasoning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.135029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a89bc6b-2403-405c-b6d1-3e3b02064ecd · outbound

This paper cites A diagram is worth a dozen images.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start A diagram is worth a dozen images

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.181520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b394d188-35fa-4666-a776-f1b32039608b · outbound

This paper cites Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.261687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d004864-0200-4949-85dc-6c912af1fa89 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start LLaVA-OneVision: Easy Visual Task Transfer

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.353238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 037b8c57-1954-4814-a83f-344cccb655ee · outbound

This paper cites LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.424523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a73e6a4-0672-489b-bf73-a3283f55e690 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Small models struggle to learn from strong reasoners

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.501039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b417db3f-86af-4854-94a3-596d2ebdd857 · outbound

This paper cites CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.565717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17c6a821-cd57-45ff-bd17-2baff1321b62 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.641119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97844a3d-0ffb-46b8-be1b-0f8825a089bd · outbound

This paper cites IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.713753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1f7142a-71bf-4066-af12-08221de474ae · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.862278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c06c8f85-6815-4e2f-a344-637fcd7bc9a1 · outbound

This paper cites Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:54.957538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c734c683-f7fa-4713-8fb2-9c415a15fa6c · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:55.080042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03176429-43cd-44e5-8e28-4dc958ab35d6 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:55.233108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c46935cb-7cb9-4e3f-b2a7-4f27b43ffc7b · outbound

This paper cites ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:55.396310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d30813e0-15f8-424e-810c-c210ec23d1a0 · outbound

This paper cites Mm-eureka: Exploring visual aha moment with rule-based large-scale reinforcement learning, 2025.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Mm-eureka: Exploring visual aha moment with rule-based large-scale reinforcement learning, 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:55.547632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31def1ef-43ec-4b2a-aa73-17b3d493d011 · outbound

This paper cites MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:55.652216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90ef9e79-5272-441e-8a41-c03e13bc9072 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:55.775370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 186b519e-bec1-4ba0-a171-e04fd64c632a · outbound

This paper cites We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:55.912190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88ea283a-40da-4d23-9579-e0f1ed81e090 · outbound

This paper cites Solving geometry problems: Combining text and diagram interpretation.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Solving geometry problems: Combining text and diagram interpretation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:56.022698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fab60022-41ec-4e5d-863b-f1e9c041f5f7 · outbound

This paper cites Rethinking Reflection in Pre-Training.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Rethinking Reflection in Pre-Training

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:56.143869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a11a1ac3-a697-4387-97e5-d8d96be010c1 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:56.300104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 343899cc-4aa0-4490-8d04-4ebe9f2a9052 · outbound

This paper cites Vlm-r1: A stable and generalizable r1-style large vision-language model.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Vlm-r1: A stable and generalizable r1-style large vision-language model

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:07.449948Z

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 06a8e1bc-ed18-460e-ac83-75c63b3af582 · outbound

This paper cites Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:56.479241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a10defa0-6cfe-4974-842b-2b1dadf18f59 · outbound

This paper cites Qvq: To see the world with wisdom, December 2024.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Qvq: To see the world with wisdom, December 2024

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:56.588932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 901117d6-9bc3-4d6e-a114-6f39238faa11 · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown, November 2024.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Qwq: Reflect deeply on the boundaries of the unknown, November 2024

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:07.178034Z

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 5af3b130-2555-4395-8ab3-95379f7f4141 · outbound

This paper cites LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:56.792142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a79d6d28-d27a-4143-bca6-a762b35c1019 · outbound

This paper cites Dart-math: Difficulty-aware rejection tuning for mathematical problem-solving.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Dart-math: Difficulty-aware rejection tuning for mathematical problem-solving

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:06.898278Z

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 9f4544bb-202d-4cd7-ac7b-b2e7a008a2d4 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:56.989615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c19e7c57-99e1-493d-8590-78bd419dba88 · outbound

This paper cites Measuring multimodal mathematical reasoning with math-vision dataset.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Measuring multimodal mathematical reasoning with math-vision dataset

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:06.644661Z

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 2d3ccf7f-34ea-4d12-9641-731228058c6f · outbound

This paper cites Math-shepherd: Verify and reinforce llms step-by-step without human annotations.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Math-shepherd: Verify and reinforce llms step-by-step without human annotations

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:06.485039Z

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 39f7e458-7dd4-4b3b-9084-63c8f4085552 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:57.363121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28084151-8b5f-460c-a165-44b5b6085461 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Chain-of-thought prompting elicits reasoning in large language models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:57.504024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f80afabf-0589-4ed3-a5eb-94ac1091de39 · outbound

This paper cites Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:57.631505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87d06979-765a-4f4f-b19d-613fc9a935fb · outbound

This paper cites Thinkpatterns-21k: A systematic study on the impact of thinking patterns in llms.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Thinkpatterns-21k: A systematic study on the impact of thinking patterns in llms

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:57.789354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 170cf958-85f6-4120-a855-822dc9e166d9 · outbound

This paper cites LLaVA-CoT: Let Vision Language Models Reason Step-by-Step.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:57.865700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f2d9f59-0262-4b0c-97d8-8aabdb75a8c0 · outbound

This paper cites Tbac-vlr1-3b-preview, 2025.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Tbac-vlr1-3b-preview, 2025

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:06.313434Z

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 7b522abf-9414-480c-adb7-a27c2fc1873c · outbound

This paper cites Qwen2.5 Technical Report.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Qwen2.5 Technical Report

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.041766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31ac8f67-bd2b-4af2-967a-3513938cd04a · outbound

This paper cites MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.101610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c410146c-2b0d-4cf1-9aec-ba6358eaa55b · outbound

This paper cites Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.218444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5d7a13f-412f-4c12-ac67-fb5593a4cba9 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Easyr1: An efficient, scalable, multi-modality rl training framework

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:06.041294Z

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 f0892b82-1770-4b4f-ac1f-d978e917377f · outbound

This paper cites Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl, 2025.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl, 2025

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.382458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d68c3269-b1d9-48f9-8ace-48cd4b1d7387 · outbound

This paper cites Perception-R1: Pioneering Perception Policy with Reinforcement Learning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Perception-R1: Pioneering Perception Policy with Reinforcement Learning

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.487945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c040f369-7c8e-4b6f-866c-e0a3ce6ec44c · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.601919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b11409-beeb-43db-9ca3-f480f5916501 · outbound

This paper cites LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.712192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4a26876-c9af-4471-865b-b57c0d141a85 · outbound

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

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? In European Conference on Computer Vision, pages 169–186

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.778569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bbde23e-4ac3-482c-8e41-cabfad96a542 · outbound

This paper cites MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:58.908022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 706c7d72-c48c-4673-9c71-8cb089abe8f8 · outbound

This paper cites Improve Vision Language Model Chain-of-thought Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Improve Vision Language Model Chain-of-thought Reasoning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:59.008711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 637323d1-858a-4d0a-b7c6-8f7a7fdfc1f7 · outbound

This paper cites Question-guided knowledge graph re-scoring and injection for knowledge graph question answering.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Question-guided knowledge graph re-scoring and injection for knowledge graph question answering

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:59.086822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb1439e-498d-4173-a198-15e309bf668b · outbound

This paper cites SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:59.184860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 482f2187-dfae-43a2-af35-2d15e290995e · outbound

This paper cites aha moment.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start aha moment

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:05.873071Z

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 ba021b73-5370-4339-b57a-0d1596a8bdde · outbound

This paper cites Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T13:12:59.356894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 088994ec-cb3d-456d-b9ef-65374c8cbcf6 · outbound

This paper cites an unresolved cited work.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:13:05.755965Z

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 90158bf8-053b-4ceb-a438-182219806833 · outbound

This paper cites aha moment.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start aha moment

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:05.620532Z

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 676068da-e025-4977-bc9c-ab3d42fc9fcf · outbound

This paper cites an unresolved cited work.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:13:05.428673Z

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 cdf8577b-67cb-4aa8-834b-6dc6274b82dd · outbound

This paper cites an unresolved cited work.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:13:05.234616Z

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 e1fe6f8b-77f7-46de-bf65-68670cf654c2 · outbound

This paper cites Given: The sum of angle B and angle D is 100◦.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Given: The sum of angle B and angle D is 100◦

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:05.011044Z

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 279d766e-1108-4a94-958d-2a37977303bb · outbound

This paper cites • Diameter BE of circle O means that BE is a straight line passing through the center of the circle.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start • Diameter BE of circle O means that BE is a straight line passing through the center of the circle

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:04.789384Z

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 3247c9e2-139e-42f3-8d06-0588b65e10cf · outbound

This paper cites Therefore, ∠BAD + ∠BCD = 180◦.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Therefore, ∠BAD + ∠BCD = 180◦

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:04.576955Z

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 d028d651-5586-4630-81be-5ad67db31a00 · outbound

This paper cites an unresolved cited work.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:13:04.430067Z

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 5ce9f604-ede0-41a4-a26a-d53905b81d6b · outbound

This paper cites an unresolved cited work.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:13:04.266127Z

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 f6db60fc-8d5a-4431-b285-6d7689142a1a · outbound

This paper cites The sum of the angles in triangle ADE is 180◦: ∠DAE + ∠ADE + ∠AED = 180◦, ∠DAE + 90◦ + ∠AED = 180◦, ∠DAE + ∠AED = 90◦.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start The sum of the angles in triangle ADE is 180◦: ∠DAE + ∠ADE + ∠AED = 180◦, ∠DAE + 90◦ + ∠AED = 180◦, ∠DAE + ∠AED = 90◦

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:04.101635Z

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 90fa580d-205b-4209-bc91-e02ff1c20b66 · outbound

This paper cites an unresolved cited work.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:13:03.931966Z

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 59d518fe-a3c8-463d-9e44-addefcc87cbc · outbound

This paper cites Since ∠DAE cannot be negative, we must re-evaluate the problem.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Since ∠DAE cannot be negative, we must re-evaluate the problem

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:03.744279Z

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 aa5d843b-6657-4ddb-8ba7-e222869a0b53 · outbound

This paper cites • Given the perimeter is 30, we can find the length of one side by dividing the perimeter by 3: Side length = 30 3 = 10.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start • Given the perimeter is 30, we can find the length of one side by dividing the perimeter by 3: Side length = 30 3 = 10

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:03.577793Z

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 1ecbf4e4-896e-4681-a351-d1a1eabead5d · outbound

This paper cites • In a 30-60-90 triangle, the ratio of the sides opposite the 30◦, 60◦, and 90◦ angles is 1 : √ 3 : 2.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start • In a 30-60-90 triangle, the ratio of the sides opposite the 30◦, 60◦, and 90◦ angles is 1 : √ 3 : 2

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:03.390783Z

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 e47c8db1-473f-4ff7-818d-48affed72784 · outbound

This paper cites • The side opposite the 30◦ angle (which is half the base) is 5 (since the base is 10 and it is bisected).

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start • The side opposite the 30◦ angle (which is half the base) is 5 (since the base is 10 and it is bisected)

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:03.218991Z

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 653666e5-8c29-49b0-a835-47748bb6a5a9 · outbound

This paper cites • We need to find the length of the altitude h of this triangle.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start • We need to find the length of the altitude h of this triangle

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:03.060938Z

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 2d11caa4-2547-4f9a-ac3b-84425752d182 · outbound

This paper cites • Let the side length of the triangle be s.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start • Let the side length of the triangle be s

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:02.880717Z

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 08494f91-4ab0-4f7c-844e-1574d2307636 · outbound

This paper cites an unresolved cited work.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:13:02.641387Z

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 ab35689a-28df-41bb-9c68-51d862c34f5b · outbound

This paper cites • In an equilateral triangle, the altitude bisects the base, creating two 30-60-90 right triangles.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start • In an equilateral triangle, the altitude bisects the base, creating two 30-60-90 right triangles

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:02.413427Z

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 7e1946b5-9ce7-45de-9b66-762df84831bd · outbound

This paper cites 5 √ 3 19.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start 5 √ 3 19

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:13:02.225475Z

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.

Pith citing papers

Observation d4ad2234-a99e-4036-ad53-08bfec05eca6 · inbound

LaRe: Latent Refocusing for Multimodal Reasoning cites this paper.

LaRe: Latent Refocusing for Multimodal Reasoning Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T00:15:16.101741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25e3e49c-c7c5-4e80-a9bb-b7981a14a940 · inbound

ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design cites this paper.

ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T07:01:49.070150Z

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 87ffdd63-c27e-425b-ae71-19dfe4e4e665 · inbound

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model cites this paper.

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:17:28.951658Z

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 2fce9b40-570a-449e-95f3-80cf80901a00 · inbound

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model cites this paper.

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:48:00.492818Z

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 2e502e2f-c1b0-4b06-9948-b3e3d3a3561b · inbound

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation cites this paper.

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:58:13.396480Z

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 7c2c75b8-0e29-456b-95e2-f9441410b598 · inbound

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation cites this paper.

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:35:00.698390Z

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 d2cfd117-e6e7-4385-82b0-78f54c0c56b1 · inbound

Distilling Game Code World Model Generation into Lightweight Large Language Models cites this paper.

Distilling Game Code World Model Generation into Lightweight Large Language Models Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:04:44.686114Z

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 d04b7a35-ab91-47a5-a8a3-3928e4eed17d · inbound

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning cites this paper.

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-07-04T19:20:06.734339Z

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 3d65458b-09dc-4312-b131-7cf8af863332 · inbound

Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement Learning cites this paper.

Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement Learning Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T06:14:18.868098Z

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 c8eb2883-164b-4563-af06-d99077909789 · inbound

SLMs as Multi-Agent Routers: A Progressive SFT and Reinforcement Learning Approach cites this paper.

SLMs as Multi-Agent Routers: A Progressive SFT and Reinforcement Learning Approach Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T01:47:07.116263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.