Paper Citation Record · LEDGER

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration

As of 8 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2607.05465.

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

pith.paper-citation-record.v1
2607.05465 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T15:24:53.016199Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

42 of 42 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7af8c52b-38d5-4a4a-acc9-7c29ef24f3b4 · outbound

This paper cites an unresolved cited work.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a523ac-a857-4ac9-9c33-9cdce6c319b0 · outbound

This paper cites Sensenova-MARS: Empowering multimodal agentic reasoning and search via reinforcement learning.arXiv preprint arXiv:2512.24330, 2025.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Sensenova-MARS: Empowering multimodal agentic reasoning and search via reinforcement learning.arXiv preprint arXiv:2512.24330, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ea1d2f4-98a9-432f-972a-8401f539e241 · outbound

This paper cites ToolScope: An agentic framework for vision-guided and long-horizon tool use.arXiv preprint arXiv:2510.27363, 2025.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration ToolScope: An agentic framework for vision-guided and long-horizon tool use.arXiv preprint arXiv:2510.27363, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b80a2fd-87a1-41fa-bf1d-0582d4bfffca · outbound

This paper cites Guid- ing instruction-based image editing via multimodal large language models.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Guid- ing instruction-based image editing via multimodal large language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2848ef5-fa2e-4880-9d1a-7fdb60429e3b · outbound

This paper cites Beyond seeing: Evaluating multimodal LLMs on tool-enabled image perception, transformation, and reasoning.arXiv preprint arXiv:2510.12712, 2025.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Beyond seeing: Evaluating multimodal LLMs on tool-enabled image perception, transformation, and reasoning.arXiv preprint arXiv:2510.12712, 2025

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0359ec15-96f7-433d-a80b-280fa4e0a837 · outbound

This paper cites Visual Programming: Compositional visual reasoning without training.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Visual Programming: Compositional visual reasoning without training

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e69bc790-2ef4-4bd5-9fe9-9d9d8116b4c1 · outbound

This paper cites DeepEyesV2: Toward Agentic Multimodal Model.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration DeepEyesV2: Toward Agentic Multimodal Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9edf56b-950f-45f0-b1e8-ffc8fecb8292 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 593f5918-d195-4542-a74a-7fe02bb5a70a · outbound

This paper cites JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75f82ed2-b139-449b-a947-9d3dae113d51 · outbound

This paper cites Jarvisevo: Towards a self-evolving photo editing agent with synergistic editor-evaluator optimization.arXiv preprint arXiv:2511.23002, 2025.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Jarvisevo: Towards a self-evolving photo editing agent with synergistic editor-evaluator optimization.arXiv preprint arXiv:2511.23002, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adb5b392-b430-4337-ab6a-a6d8c94c1f11 · outbound

This paper cites Chameleon: Plug-and-play compositional reasoning with large language models.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Chameleon: Plug-and-play compositional reasoning with large language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb0967b-3959-48da-b05f-d884dbc8030f · outbound

This paper cites Pico-banana-400k: A large-scale dataset for text-guided image editing, 2025.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Pico-banana-400k: A large-scale dataset for text-guided image editing, 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05e83d41-7ea8-4f13-bedf-0952e51627ef · outbound

This paper cites High- resolution image synthesis with latent diffusion models.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration High- resolution image synthesis with latent diffusion models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7beb81d-456f-4cde-99c4-a5a6ca8783d3 · outbound

This paper cites Fleet, and Mohammad Norouzi.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Fleet, and Mohammad Norouzi

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbfdf901-09a1-4bf3-b49b-102eee7215fc · outbound

This paper cites Proximal Policy Optimization Algorithms.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Proximal Policy Optimization Algorithms

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ebaf06-0380-4f2e-b2b1-c405ca6b8320 · outbound

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

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3197a0f2-71d7-473e-9133-04261f759ec2 · outbound

This paper cites ZoomEye: Enhancing multimodal LLMs with human-like zooming capabilities through tree-based image exploration.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration ZoomEye: Enhancing multimodal LLMs with human-like zooming capabilities through tree-based image exploration

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 073c118f-7b32-42ba-baba-50c4ca921747 · outbound

This paper cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98267f55-a184-4821-96d8-722237dc1155 · outbound

This paper cites Emu Edit: Precise Image Editing via Recognition and Generation Tasks.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Emu Edit: Precise Image Editing via Recognition and Generation Tasks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 920922f2-6c72-48c4-afd8-5e17bcf4bdd7 · outbound

This paper cites Codedance: A dynamic tool-integrated MLLM for executable visual reasoning.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Codedance: A dynamic tool-integrated MLLM for executable visual reasoning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a87fb1-937f-47ee-ae92-86e720b211e1 · outbound

This paper cites OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 475d80b8-ec20-4910-aea7-8c0f3ca4bc1e · outbound

This paper cites ViperGPT: Visual Inference via Python Execution for Reasoning.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration ViperGPT: Visual Inference via Python Execution for Reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 483223c2-d70c-46c9-a9da-0dd4d9d7f714 · outbound

This paper cites AdaTooler-V: Adaptive Tool-Use for Images and Videos.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration AdaTooler-V: Adaptive Tool-Use for Images and Videos

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b9edc69-2b52-40a9-b50f-90c37ec7888d · outbound

This paper cites Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd99e533-0839-4a77-9aae-817b237a98de · outbound

This paper cites Qwen-Image Technical Report.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Qwen-Image Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0058b84e-3db6-4097-8ba6-ec4ad83f4553 · outbound

This paper cites Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db4963ce-c8f2-413d-a49f-f38173e4dbf4 · outbound

This paper cites MMSearch-R1: Incentivizing LMMs to Search.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration MMSearch-R1: Incentivizing LMMs to Search

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f5fc1fc-fe86-440c-9020-925cf50e605d · outbound

This paper cites Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 866d5f14-c40e-4e54-a508-b93d2adcfd23 · outbound

This paper cites MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2ad1a3a-313e-4f43-a3a3-aa01379c0ac8 · outbound

This paper cites Narasimhan, and Yuan Cao.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Narasimhan, and Yuan Cao

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95fe9acc-68f7-4cd5-bc0f-d97ced38e83d · outbound

This paper cites MagicBrush: A manually annotated dataset for instruction-guided image editing.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration MagicBrush: A manually annotated dataset for instruction-guided image editing

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb24a7f7-f626-4361-bf99-a8ccc27eded0 · outbound

This paper cites Tool-R1: Sample-efficient reinforcement learning for agentic tool use.arXiv preprint arXiv:2509.12867, 2025.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Tool-R1: Sample-efficient reinforcement learning for agentic tool use.arXiv preprint arXiv:2509.12867, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9412f523-83c7-4034-ba53-801ffdf9dd13 · outbound

This paper cites Thyme: Think Beyond Images.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Thyme: Think Beyond Images

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c3b21be-b2fa-4add-af4d-4b42ff7626f4 · outbound

This paper cites Skywork-R1V4: Toward agentic multimodal intelligence through interleaved thinking with images and deepresearch.arXiv preprint arXiv:2512.02395, 2025.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Skywork-R1V4: Toward agentic multimodal intelligence through interleaved thinking with images and deepresearch.arXiv preprint arXiv:2512.02395, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90cd6298-e4a7-4061-9495-76b0817be375 · outbound

This paper cites PyVision: Agentic Vision with Dynamic Tooling.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration PyVision: Agentic Vision with Dynamic Tooling

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455e962a-f598-4f3f-bd25-de20a1756747 · outbound

This paper cites DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7012fe28-4b2d-4ecb-a0a0-3e16095da419 · outbound

This paper cites an unresolved cited work.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad232445-1fa0-45bc-9e76-0408d524d824 · outbound

This paper cites an unresolved cited work.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a708d7-c68a-48fe-9185-8a2fcf6b707f · outbound

This paper cites Focus on semantic correctness, requested objects/actions, positions, colors, text, preservation of the input image when editing, and overall visual fidelity.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Focus on semantic correctness, requested objects/actions, positions, colors, text, preservation of the input image when editing, and overall visual fidelity

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af624ed-6575-441a-afc3-c088c7290837 · outbound

This paper cites an unresolved cited work.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Unresolved cited work

Reference 41

Resolution: parse uncertain; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9758187b-7eea-4c46-83a8-a2cf9d1f6bc5 · outbound

This paper cites an unresolved cited work.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50be376e-7ecb-4a8e-95bc-7bce008c0938 · outbound

This paper cites score": 0.0} 17 Table 7: Distribution of tool-chain types in CanvasCraft-SFT. The “Multi-tool Hard.

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration score": 0.0} 17 Table 7: Distribution of tool-chain types in CanvasCraft-SFT. The “Multi-tool Hard

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-11T15:24:53.016199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.