Paper Citation Record · LEDGER

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs

As of 7 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 3 inbound Pith citation observations for arXiv:2507.07562.

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

pith.paper-citation-record.v1
2507.07562 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:43:14.663362Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T22:56:39.504430Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T00:14:04.589912Z

Reference resolution

26 of 26 outbound references displayed

verified exact1
verified fuzzy1
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 89f1901c-ae94-490e-954f-677cf57d7bd4 · outbound

This paper cites Qwen2.5-VL Technical Report.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.071992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb82a37-d36b-4c55-8e65-504b2137b1ba · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.351683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7118bfb-52ae-451f-9256-f4511780ad8c · outbound

This paper cites Arcee’s mergekit: A toolkit for merging large language models.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Arcee’s mergekit: A toolkit for merging large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:43:15.589359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 932dcfa6-612f-4c2d-8d19-603af71bc7d9 · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.533076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f42d94-ef92-4dc4-9138-292463bcf64b · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.605646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18ada49c-25ff-477c-8b05-69225c260b51 · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Measuring Mathematical Problem Solving With the MATH Dataset

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.666793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f53ea69e-b35b-4a47-9013-8d1695fc6b97 · outbound

This paper cites OpenAI o1 System Card.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs OpenAI o1 System Card

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.819360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 715a276c-f616-4c4e-a226-32d82389387f · outbound

This paper cites AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.895530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30494fb6-9a92-41d0-854e-af82ae08b37c · outbound

This paper cites s1: Simple test-time scaling.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs s1: Simple test-time scaling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.038090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 607f44a6-7c83-4c6a-958e-4ea33e61a483 · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.127934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0947f061-f8f4-4fd4-8074-0c15a6b01239 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs HybridFlow: A Flexible and Efficient RLHF Framework

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.188974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 042fe905-15a9-48d6-afaf-1cd6fcb6b17b · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.310210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4252390-13a8-40bd-94b3-5c13a46eaf1e · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.368576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c3f7eaa-e072-4070-a191-14f807f18d2d · outbound

This paper cites Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.461715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a7de96f-9c1e-4d68-87df-a3574142399b · outbound

This paper cites R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.654093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00d0a4b-b544-4070-b08a-39500efd0c46 · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.832356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee5f3f58-337f-41bf-9cac-c7137806a94d · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:14.145096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6993364a-f058-445a-91fb-b92c2850bc60 · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:14.386503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f15e2a6-df26-4486-8f23-3ba1178ff97a · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Improve Vision Language Model Chain-of-thought Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:14.536799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66bb2bd0-6a99-4730-a655-82aeb47e628b · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:14.663362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da25105-e8bd-433c-94ea-55230efbd11f · outbound

This paper cites Reason-rft: Reinforcement fine-tuning for visual reasoning.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Reason-rft: Reinforcement fine-tuning for visual reasoning

Reference 1985

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.245905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6a0d5fc-8fa4-4230-8d97-50b9bb59abc6 · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.737770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24224149-d2cf-4f44-9874-6ae319720223 · outbound

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

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:13.535549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49fea811-4015-426c-b542-f2c90b4fdc51 · outbound

This paper cites MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.963346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565eaac8-595a-41a9-8e04-6a1bf00cc9b3 · outbound

This paper cites Unlocking the potential of difficulty prior in rl-based multimodal reasoning.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs Unlocking the potential of difficulty prior in rl-based multimodal reasoning

Reference 2024

Resolution: verified exact; raw_fallback, observed 2026-08-06T18:43:15.339676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c2b2560b-81c8-414e-9bd5-0cbebde45c4d · outbound

This paper cites SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models.

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T18:43:12.147943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4220cfe6-f0bf-41ee-88f0-de5c6f8eacec · inbound

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

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:40:41.815805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4fd3e50a-a2b5-42db-8bf4-dda52bf77160 · inbound

On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training cites this paper.

On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-16T14:48:00.469365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd0ea6f6-0c41-48e7-8da5-e4f535269f7b · inbound

AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution cites this paper.

AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-30T00:14:04.591636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.