Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning | Paper Citation Record

Observation 21d126e9-bc08-49be-ac7a-28c7872f3451 · outbound

This paper cites Latent reasoning with supervised thinking states.arXiv preprint arXiv:2602.08332, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Latent reasoning with supervised thinking states.arXiv preprint arXiv:2602.08332, 2026

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.922601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b40b537-9d4c-4dae-87c7-72e0cbaead1d · outbound

This paper cites Acloserlookatbiasandchain-of-thought faithfulness of large (vision) language models.arXiv preprint arXiv:2505.23945, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Acloserlookatbiasandchain-of-thought faithfulness of large (vision) language models.arXiv preprint arXiv:2505.23945, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.930040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54c530f6-4381-45b3-8282-d55da1520d61 · outbound

This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.935715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4127ec8f-cb29-49ef-bf11-6a0e20ae4c03 · outbound

This paper cites MMStar: An evaluator-centric benchmark for multi-modal large language models, 2024.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning MMStar: An evaluator-centric benchmark for multi-modal large language models, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.941754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3a06ba7-1a84-4d28-9062-55bd6db2c470 · outbound

This paper cites Perception before reasoning: Two-stage reinforcement learning for visual reasoning.arXiv preprint arXiv:2509.13031, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Perception before reasoning: Two-stage reinforcement learning for visual reasoning.arXiv preprint arXiv:2509.13031, 2025

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.947142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1d6048d-a793-41d2-8a99-295b545a062e · outbound

This paper cites Reasoning Models Don't Always Say What They Think.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Reasoning Models Don't Always Say What They Think

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.952698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 527f98d2-c979-4acc-b913-fbf7eec197af · outbound

This paper cites v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.959442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2e1502-e09d-4db2-af0d-9f9e3250c7e9 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.964796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 509a382a-9523-41ba-98f9-4c79aa25a0ef · outbound

This paper cites Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.970205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93107529-ff1e-4d89-8ff6-a0d9f5579f93 · outbound

This paper cites Virgo: A Preliminary Exploration on Reproducing o1-like MLLM.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Virgo: A Preliminary Exploration on Reproducing o1-like MLLM

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.978385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65d3ed44-1f15-4843-b40c-8316c5ac469c · outbound

This paper cites Revisiting the necessity of lengthy chain-of-thought in vision-centric reasoning.arXiv preprint arXiv:2511.22586, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Revisiting the necessity of lengthy chain-of-thought in vision-centric reasoning.arXiv preprint arXiv:2511.22586, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.984603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be44b9db-1f68-4022-8868-c22a5ce9043b · outbound

This paper cites VLMEvalKit: An open-source toolkit for evaluating large multi-modality models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning VLMEvalKit: An open-source toolkit for evaluating large multi-modality models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.990131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7931aa8e-29c5-4a9f-9949-92b81a812407 · outbound

This paper cites GRIT: Teaching MLLMs to Think with Images.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning GRIT: Teaching MLLMs to Think with Images

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:13.996266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9056dd3f-3141-49d4-8937-2bf9ac597373 · outbound

This paper cites Reward Shaping to Mitigate Reward Hacking in RLHF.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.002043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 195d31a5-11c3-492e-af18-b14ebf648ec6 · outbound

This paper cites BLINK: Multimodal Large Language Models Can See but Not Perceive.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning BLINK: Multimodal Large Language Models Can See but Not Perceive

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.008737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d7c8d5-a9f5-446f-ab58-b427e8915449 · outbound

This paper cites Thinking with deltas: Incen- tivizingreinforcementlearningviadifferentialvisualreasoningpolicy.arXivpreprintarXiv:2601.06801, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Thinking with deltas: Incen- tivizingreinforcementlearningviadifferentialvisualreasoningpolicy.arXivpreprintarXiv:2601.06801, 2026

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.016201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 068e1c91-7dab-46d4-be3a-3a5502407ccd · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Gemini: A Family of Highly Capable Multimodal Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.021564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a332fe5b-83bd-4f84-a92e-1559c14595f7 · outbound

This paper cites GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.026958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0456dc97-cbd6-472e-9331-b839f796af49 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Visual programming: Compositional visual reasoning without training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.032344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e15c4967-d4e1-4555-9a7d-b39829d8404d · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Training Large Language Models to Reason in a Continuous Latent Space

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.037446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 661bcc98-115d-42d1-af70-47b2e98f38f0 · outbound

This paper cites DeepEyesV2: Toward Agentic Multimodal Model.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning DeepEyesV2: Toward Agentic Multimodal Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.046256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caeb8699-53c6-4525-ae64-b3f61ae401e4 · outbound

This paper cites Hollon, and Bryan Wang.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Hollon, and Bryan Wang

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.052496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24edadf1-b96c-40e0-b450-1d1055e80bc6 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.059008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2688c6b2-61ba-4f3a-b127-b6d76bfd8826 · outbound

This paper cites VerlTool: Towards holistic agentic reinforcement learning with tool use.arXiv preprint arXiv:2509.01055, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning VerlTool: Towards holistic agentic reinforcement learning with tool use.arXiv preprint arXiv:2509.01055, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.065378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f00b1d-851b-48ac-9c49-cf03c313ff85 · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Kimi K2.5: Visual Agentic Intelligence

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.072026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b105647b-87f3-4fb7-82bf-6f0446626b1f · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.077712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2897de1e-e8b0-45dd-9850-acec5ccdf6bc · outbound

This paper cites Measuring Faithfulness in Chain-of-Thought Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.083137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35cf9fd5-68e4-40d2-972e-a5679640d9ca · outbound

This paper cites Zebra-cot: A dataset for interleaved vision language reasoning.arXiv preprint arXiv:2507.16746, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Zebra-cot: A dataset for interleaved vision language reasoning.arXiv preprint arXiv:2507.16746, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.088153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d54afa-1dd1-45c7-bd61-5613d7a3532b · outbound

This paper cites Tir-bench: A comprehensive benchmark for agentic thinking-with-images reasoning.arXiv preprint arXiv:2511.01833, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Tir-bench: A comprehensive benchmark for agentic thinking-with-images reasoning.arXiv preprint arXiv:2511.01833, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.092965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6155944d-2c98-4ebf-ac10-b83d52418bbb · outbound

This paper cites Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.097596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c4c7087-0bf3-4c1c-ba1f-f214947de793 · outbound

This paper cites On the faithfulness of visual thinking: Measurement and enhancement.arXiv preprint arXiv:2510.23482, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning On the faithfulness of visual thinking: Measurement and enhancement.arXiv preprint arXiv:2510.23482, 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.102763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fed3ace4-7f7a-4068-a766-df90f1678d4d · outbound

This paper cites Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.107674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e485d8-49de-4c3a-9605-ae3b6734b188 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Chameleon: Plug-and-play compositional reasoning with large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.113186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9004a401-c7d2-49cc-ba01-b07b1b464f24 · outbound

This paper cites Reasoning Models Can Be Effective Without Thinking.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Reasoning Models Can Be Effective Without Thinking

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.118396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e7c981-a900-4a4f-9443-7f23e41f7676 · outbound

This paper cites What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.125300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c9b6ca7-8c46-4542-b286-5c2210ec5976 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.131378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d915d33d-2552-490f-b362-54b7e010fd32 · outbound

This paper cites GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.137144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d5594e-04c8-45a8-9b98-56a44e4122d7 · outbound

This paper cites Show Your Work: Scratchpads for Intermediate Computation with Language Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Show Your Work: Scratchpads for Intermediate Computation with Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.143566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab05b758-cb33-47e7-92ea-c69c2c1dc7d4 · outbound

This paper cites GPT-4 Technical Report.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning GPT-4 Technical Report

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.149920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29b9e7f1-eedf-448c-beb2-59ffb461b6e5 · outbound

This paper cites Thinking with images.https://openai.com/index/thinking-with-images/, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Thinking with images.https://openai.com/index/thinking-with-images/, 2025

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.156357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a9f1ba0-82a1-4a24-ae45-3cfb98252cde · outbound

This paper cites Do MLLMs really see it: Reinforcing visual attention in multimodal LLMs.arXiv preprint arXiv:2602.08241, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Do MLLMs really see it: Reinforcing visual attention in multimodal LLMs.arXiv preprint arXiv:2602.08241, 2026

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.161693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9a368e4-f37a-4ffd-b1d6-20ad3b5f427f · outbound

This paper cites CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.169132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d47f3c4d-f832-4c6b-a745-c38dbd5f852b · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.175515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25ad21de-9c81-4709-b03a-9f0f39708c29 · outbound

This paper cites Qwen2.5-VL Technical Report.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Qwen2.5-VL Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.182177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0aada3-d18d-4ebe-83af-b05f2c1bd462 · outbound

This paper cites Qwen3-VL Technical Report.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Qwen3-VL Technical Report

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.188571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa21b7df-5558-4e33-8163-a62a77acc62f · outbound

This paper cites Vision language models are blind: Failing to translate detailed visual features into words.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Vision language models are blind: Failing to translate detailed visual features into words

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.194557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b553977f-9a03-4e10-9724-7816c539dd03 · outbound

This paper cites Grounded Reinforcement Learning for Visual Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Grounded Reinforcement Learning for Visual Reasoning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.200723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71aed7c4-6d94-4238-a052-da220eee155a · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Toolformer: Language models can teach themselves to use tools

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.206226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb554f4a-9642-4522-ac1f-13538d74085c · outbound

This paper cites Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.211374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36606029-2231-4dbc-87b7-538e2926826a · outbound

This paper cites HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.216761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d80610d9-2730-4bd8-bb41-1c6a246f93d8 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning HybridFlow: A Flexible and Efficient RLHF Framework

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.221402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7039400c-ff0f-4515-a00c-e38454fb4b39 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Reflexion: Language agents with verbal reinforcement learning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.226408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd7094a6-99ef-4afb-b609-325ea8259745 · outbound

This paper cites Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.231434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f895714-0304-4781-afac-8325cbee7e5e · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.237048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6adf3fcd-a92f-4e84-9f6c-f35f8fdca13d · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.243692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 808134bd-c4aa-41ce-8ced-e241ff856bee · outbound

This paper cites When thinking hurts: Mitigating visual forgetting via frame repetition.arXiv preprint arXiv:2603.16256, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning When thinking hurts: Mitigating visual forgetting via frame repetition.arXiv preprint arXiv:2603.16256, 2026

Reference 56

Resolution: verified exact; raw_fallback, observed 2026-08-11T12:53:16.994849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 33cfd61d-327a-47bf-831c-7f2f998d7ef9 · outbound

This paper cites FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-08-11T12:53:16.902776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a6faa050-844b-4cd5-9dc9-5a37b4bcd364 · outbound

This paper cites ViperGPT: Visual inference via python execution for reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning ViperGPT: Visual inference via python execution for reasoning

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.260904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c664eea2-5da5-491d-a904-af12e5d86968 · outbound

This paper cites CV-Bench: A computer vision benchmark for evaluating visual perception in multimodal language models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning CV-Bench: A computer vision benchmark for evaluating visual perception in multimodal language models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.266490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984d86a0-d722-4cdd-a983-895defd786b0 · outbound

This paper cites an unresolved cited work.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.271924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb4caa7c-52de-4d80-8dba-fa757ff24771 · outbound

This paper cites Journey before destination: Visual faithfulness in slow thinking.arXiv preprint arXiv:2512.12218, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Journey before destination: Visual faithfulness in slow thinking.arXiv preprint arXiv:2512.12218, 2025

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.277132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa0df45c-08c5-43d0-8474-d7483c923177 · outbound

This paper cites GeoEyes: On-demand visual focusing for ultra-high-resolution remote sensing.arXiv preprint arXiv:2602.14201, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning GeoEyes: On-demand visual focusing for ultra-high-resolution remote sensing.arXiv preprint arXiv:2602.14201, 2026

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.282612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fcc6dce-7fe1-493b-953e-1838a6248d78 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.289490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 431c9e90-1e5c-4855-8d17-1096829a3f45 · outbound

This paper cites PLaT: Latent chain-of-thought as planning: Decoupling reasoning from verbalization.arXiv preprint arXiv:2601.21358, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning PLaT: Latent chain-of-thought as planning: Decoupling reasoning from verbalization.arXiv preprint arXiv:2601.21358, 2026

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.295877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13f7fe4e-f9e3-4b26-924d-51d354c8d659 · outbound

This paper cites VAGEN: Reinforcing world model reasoning for multi-turn VLM agents.arXiv preprint arXiv:2510.16907, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning VAGEN: Reinforcing world model reasoning for multi-turn VLM agents.arXiv preprint arXiv:2510.16907, 2025

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.301424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 155234b5-f117-43e0-ac3f-685adee465c4 · outbound

This paper cites Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.307438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad4de20a-fa87-4e81-a3f1-935df8556f00 · outbound

This paper cites A practitioner’s guide to multi-turn agentic reinforcement learning.arXiv preprint arXiv:2510.01132, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning A practitioner’s guide to multi-turn agentic reinforcement learning.arXiv preprint arXiv:2510.01132, 2025

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.313080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e8456bd-7ef2-4fdb-86cb-b3b5d1e618a7 · outbound

This paper cites Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.318402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f574102a-4bd5-4cf0-aaab-eeb6bc7aa745 · outbound

This paper cites Self-consistency improves chain of thought reasoning in language models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Self-consistency improves chain of thought reasoning in language models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.324074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11876701-c04c-48cb-9602-4d5af4eb6f62 · outbound

This paper cites Simple o3: Towards Interleaved Vision-Language Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Simple o3: Towards Interleaved Vision-Language Reasoning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.330057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672af4c4-9a5f-40d2-abde-ad12cb180fd6 · outbound

This paper cites RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.335916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58bc7e5f-585b-444a-b826-0f46909038fb · outbound

This paper cites CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.341547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6834941-8cc1-470f-bd19-d04bb69d18b4 · outbound

This paper cites V-FAT: Benchmarking visual fidelity against text-bias.arXiv preprint arXiv:2601.04897, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning V-FAT: Benchmarking visual fidelity against text-bias.arXiv preprint arXiv:2601.04897, 2025

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.346906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75cb0d3c-04e6-46b5-a8e7-454ba0800c7b · outbound

This paper cites Chi, Quoc V.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Chi, Quoc V

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.352064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8614fd79-8787-43d5-83b9-21608da229f4 · outbound

This paper cites Zooming without zooming: Region- to-image distillation for fine-grained multimodal perception.arXiv preprint arXiv:2602.11858, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Zooming without zooming: Region- to-image distillation for fine-grained multimodal perception.arXiv preprint arXiv:2602.11858, 2026

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.357126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10131f61-7daf-46c1-82f6-f0f69697db60 · outbound

This paper cites Visual generation unlocks human-like reasoning through multimodal world models.arXiv preprint arXiv:2601.19834, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Visual generation unlocks human-like reasoning through multimodal world models.arXiv preprint arXiv:2601.19834, 2026

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.362216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 812332c9-4101-4395-ad7a-532e7f106164 · outbound

This paper cites VTool-R1: VLMs learn to think with images via reinforcement learning on multimodal tool use.arXiv preprint arXiv:2505.19255, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning VTool-R1: VLMs learn to think with images via reinforcement learning on multimodal tool use.arXiv preprint arXiv:2505.19255, 2025

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.367385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1358137-74bd-4884-b10f-9687c7390116 · outbound

This paper cites V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.372654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39fdb19d-0830-48e0-bb5b-af6e36d48e4a · outbound

This paper cites Tool-augmented policy optimization.arXiv preprint arXiv:2510.07038, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Tool-augmented policy optimization.arXiv preprint arXiv:2510.07038, 2025

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.378336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2e8fa83-702f-44e8-bdb0-0b664623ccfd · outbound

This paper cites Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.384423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0bf9a99-100f-4ea1-aa7d-15c558030ec7 · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.390585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68cb5366-89ba-4258-9f1a-99d967af8c4c · outbound

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

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.396078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51316cec-d858-4612-af50-38963eb96922 · outbound

This paper cites Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.403481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22ace32-3b90-4012-b5f8-9e466331462e · outbound

This paper cites Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.409420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e606f51-b262-42b5-8073-9e895eb919f4 · outbound

This paper cites VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.415257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af5e4430-ad7c-4533-b666-a57b79c4825d · outbound

This paper cites Look-Back: Implicit Visual Re-focusing in MLLM Reasoning.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.422649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c46a5d03-1cee-489d-98bd-52fb90f9d5b4 · outbound

This paper cites Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization

Reference 87

Resolution: verified exact; local_arxiv, observed 2026-08-11T12:53:15.665161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6dc2fa7b-8836-4961-aa4b-e74d4e6e85d4 · outbound

This paper cites Thinking with images via self-calling agent.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Thinking with images via self-calling agent

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.434700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebbc4565-7328-45a9-9e9e-c80012b9984e · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Tree of thoughts: Deliberate problem solving with large language models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.440324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e03bf6e-d596-4191-833a-6f05b55e852a · outbound

This paper cites React: Synergizing reasoning and acting in language models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning React: Synergizing reasoning and acting in language models

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.445645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb86f08f-a4d6-4b04-937e-b32d0aaac4c4 · outbound

This paper cites an unresolved cited work.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Unresolved cited work

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.450944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93488707-e50d-4f90-8a7d-95b8d82a412d · outbound

This paper cites ProRL agent: Rollout-as-a-service for reinforcement learning training of multi-turn LLM agents.arXiv preprint arXiv:2603.18815, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning ProRL agent: Rollout-as-a-service for reinforcement learning training of multi-turn LLM agents.arXiv preprint arXiv:2603.18815, 2026

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.456716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da67c1b-6c4a-472f-93ea-6f3d8f059e62 · outbound

This paper cites MM-CoT: A benchmark for probing visual chain-of-thought reasoning.arXiv preprint arXiv:2512.08228, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning MM-CoT: A benchmark for probing visual chain-of-thought reasoning.arXiv preprint arXiv:2512.08228, 2025

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.462467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cde152f-f8de-45dd-8e0e-f00f4a94f582 · outbound

This paper cites LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.468007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef2d5d0a-b1e9-435e-9982-f1221d152fad · outbound

This paper cites MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.474606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c12feb7b-3ba7-47e1-a0bc-5cb150c124f2 · outbound

This paper cites Thyme: Think Beyond Images.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Thyme: Think Beyond Images

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.480733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fb149dd-5d29-49f4-a574-6c1c48b07001 · outbound

This paper cites Skywork-r1v4: Toward agentic multimodal intelligence through interleaved thinking with images and deepresearch.arXiv preprint arXiv:2512.02395, 2025.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Skywork-r1v4: Toward agentic multimodal intelligence through interleaved thinking with images and deepresearch.arXiv preprint arXiv:2512.02395, 2025

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.486447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a376dd0-d944-496d-b3da-cffe00b77a20 · outbound

This paper cites CM2: Reinforcement learning with checklist rewards for multi-turn and multi-step agentic tool use.arXiv preprint arXiv:2602.12268, 2026.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning CM2: Reinforcement learning with checklist rewards for multi-turn and multi-step agentic tool use.arXiv preprint arXiv:2602.12268, 2026

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.491968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abebf7fd-87a9-4b5f-ad26-07e75afc7002 · outbound

This paper cites Multimodal Chain-of-Thought Reasoning in Language Models.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning Multimodal Chain-of-Thought Reasoning in Language Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.497323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 754fb110-bb38-4730-85a6-4d1842ee219b · outbound

This paper cites On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs.

Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-11T12:53:14.503030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers