Paper Citation Record · LEDGER

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification

As of 7 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2607.28225.

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

pith.paper-citation-record.v1
2607.28225 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T14:08:11.249722Z

measured 26 of 26 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy0
unresolved25
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8fa4e668-6590-46fe-9b7c-0c84de0cd499 · outbound

This paper cites ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.175717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6efdafa-ddac-4b0e-b7a3-619f8a91e288 · outbound

This paper cites Advancing vision-language models in front-end development via data synthesis.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Advancing vision-language models in front-end development via data synthesis

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.179287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f512032d-254b-47f2-87eb-d19703f09462 · outbound

This paper cites Large Language Model based Multi-Agents: A Survey of Progress and Challenges.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.182691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2056aca3-852b-44cd-bddd-5cdd8dd31922 · outbound

This paper cites GPT-4o System Card.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification GPT-4o System Card

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.189609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f45ecf27-0a78-4eae-a085-aaecdbe7b6d1 · outbound

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

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification LLaVA-OneVision: Easy Visual Task Transfer

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.196715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3fe7b7-6513-4933-82f0-3ab256eedac8 · outbound

This paper cites Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.200135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1738387-2a5d-4b56-b4c0-2b4929d143e2 · outbound

This paper cites Decoupled Weight Decay Regularization.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Decoupled Weight Decay Regularization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.203722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a609a9-7f5a-4cc5-9de1-c36ffd04a70e · outbound

This paper cites ChatDev: Communicative Agents for Software Development.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification ChatDev: Communicative Agents for Software Development

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.210412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df46d5d9-fd55-48cd-a8dd-0fcf0baffebd · outbound

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

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.213839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05725049-4968-40be-ba2f-eb42ed40ef94 · outbound

This paper cites Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.217082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 673afc8b-8945-4379-ab7e-8b4a898275e2 · outbound

This paper cites Kwai Keye-VL Technical Report.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Kwai Keye-VL Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.220405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb046770-e1ee-4425-9edf-2abf15cb33df · outbound

This paper cites Multi-Agent Collaboration Mechanisms: A Survey of LLMs.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.224025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 362fce86-b7c8-4b40-9178-c9b669c08e65 · outbound

This paper cites From illusion to intention: Visual rationale learning for vision-language reasoning.arXiv preprint arXiv:2511.23031, 2025a.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification From illusion to intention: Visual rationale learning for vision-language reasoning.arXiv preprint arXiv:2511.23031, 2025a

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.227842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c655b6a0-a763-4853-bd6e-c897f7c6fd36 · outbound

This paper cites Divide, conquer and combine: A training-free framework for high- resolution image perception in multimodal large language models.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Divide, conquer and combine: A training-free framework for high- resolution image perception in multimodal large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.230720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5b817ab-bd97-4676-bf30-c6b918c577db · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.234071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a7208e3-3c70-4675-b4e5-961263fd1b7f · outbound

This paper cites Visual planning: Let’s think only with images.arXiv preprint arXiv:2505.11409,.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Visual planning: Let’s think only with images.arXiv preprint arXiv:2505.11409,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.237373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4920509b-3647-47ce-afd9-a40d336c0955 · outbound

This paper cites Wenxi Yang, Yuzhong Zhao, Fang Wan, and Qixiang Ye.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Wenxi Yang, Yuzhong Zhao, Fang Wan, and Qixiang Ye

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.240214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f68406-5f9f-496c-b3a2-8f6e11c5da4b · outbound

This paper cites R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.243120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c2eac63-23ca-4c73-be3a-eb43dd5ff5bf · outbound

This paper cites All scores are averaged over the rollouts within the batch.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification All scores are averaged over the rollouts within the batch

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.246530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 722c9621-d1da-4de2-81d5-71a440f109e2 · outbound

This paper cites {file_path}.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification {file_path}

Reference 26

Resolution: malformed identifier; no resolver link, observed 2026-07-31T14:08:11.249722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19f4851a-0d9a-4daa-b587-2a7ef3bac2f6 · outbound

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

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.206984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58b399bf-5783-4577-a337-846ff0a740fc · outbound

This paper cites Qwen3-VL Technical Report.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Qwen3-VL Technical Report

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.164039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c505a3-8516-404f-bb1d-243a002acfdb · outbound

This paper cites Thinking with Generated Images.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Thinking with Generated Images

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.168680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9c234a2-ad50-4ce5-a0b9-6321539621fa · outbound

This paper cites Controlthinker: Unveiling latent semantics for controllable image generation through visual reasoning.arXiv preprint arXiv:2506.03596,.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Controlthinker: Unveiling latent semantics for controllable image generation through visual reasoning.arXiv preprint arXiv:2506.03596,

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.186512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc5c28dd-441f-4682-a515-5d5a635e3a87 · outbound

This paper cites A survey on the optimization of large language model-based agents.arXiv preprint arXiv:2503.12434,.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification A survey on the optimization of large language model-based agents.arXiv preprint arXiv:2503.12434,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.172286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25c1bf69-7aec-4a29-be85-5c4230954669 · outbound

This paper cites Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search.

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-07-31T14:08:11.193418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.