Pith. sign in

Paper Citation Record · LEDGER

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

As of 20 August 2026, this Paper Citation Record lists 100 of 106 outbound references and 5 inbound Pith citation observations for arXiv:2506.08012.

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

pith.paper-citation-record.v1
2506.08012 v1

Coverage vector

measured 100 of 106 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:25:59.525256Z

measured 105 of 105 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T17:38:50.313305Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

100 of 106 outbound references displayed

  • verified exact0
  • verified fuzzy29
  • unresolved71
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation fdb9a801-80dc-44de-b74e-d22ee3912f76 · outbound

This paper cites Agent S: An Open Agentic Framework that Uses Computers Like a Human.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Agent S: An Open Agentic Framework that Uses Computers Like a Human

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.211146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.211146Z digest=sha256:41cf064fec81691de82e629fc8e592e95fffc3afd426757574b7711d75612956

Observation 6ea73e42-b8e2-4fc5-bd8b-44506e0efaa8 · outbound

This paper cites Wave-UI Dataset.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Wave-UI Dataset

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.215016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.215016Z digest=sha256:3856b4b3f4e62524e9d304ab092a3313912aa32a74ed7f771a8e6a4e6a4c8996

Observation c77efc84-308d-442a-b064-f67950b41f1f · outbound

This paper cites Wave-UI-25K Dataset.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Wave-UI-25K Dataset

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.218004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.218004Z digest=sha256:4cff9ad0a6a2f836591fffb63f5fedb781440219ddb05741c413858f8e9b9a21

Observation 451c5d0c-3b0c-47c8-a287-d2c0ba012cd8 · outbound

This paper cites Claude 3.5 sonnet.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Claude 3.5 sonnet

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.220969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.220969Z digest=sha256:db8813b46d241daac362f5146ee74d3d564ea7dd64bcbdf3a4c18f9f33ec18e2

Observation dee1b3a4-8b09-4520-b846-54d8d9c8ac1e · outbound

This paper cites Screenai: A vision-language model for ui and infographics understanding.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Screenai: A vision-language model for ui and infographics understanding

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.223801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.223801Z digest=sha256:f5243d816fcd68f577993f38e43de649bc40e83125b9c1a313e2527f5b92a58d

Observation 82ccf694-85b9-4fe8-8f40-b5ec71d08f30 · outbound

This paper cites Uibert: Learning generic multimodal representations for ui understanding.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Uibert: Learning generic multimodal representations for ui understanding

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.227381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.227381Z digest=sha256:d617edd97d27465a610668f87de246553c419bb0104830216b55b6d4bf26af24

Observation ad01e14f-f568-4893-a43d-b0afa9e9de4c · outbound

This paper cites DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.230422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.230422Z digest=sha256:e6aef0147c9a37116401e209fc7ee7d125a042c9a4a6a716354d0f34c24773ef

Observation 75b3ab44-ebd8-4121-96b3-9a7bcdab83a2 · outbound

This paper cites Digi-Q: Learning Q-Value Functions for Training Device-Control Agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Digi-Q: Learning Q-Value Functions for Training Device-Control Agents

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.234111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.234111Z digest=sha256:62d679fbd8ad6343b0dea9a11e1f5d63d965c97e30833a769be223d662a43cc9

Observation 11623fba-b0c1-4acd-8340-8bc403d5424c · outbound

This paper cites Qwen2.5-VL Technical Report.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Qwen2.5-VL Technical Report

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.236896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.236896Z digest=sha256:a14c82ef00969e286ead62517c4f6a96b7058de034141da14e6afae193e2fda6

Observation d26740be-6548-447f-968b-516e47645102 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.239507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.239507Z digest=sha256:ee70967437cc75417eb8d5b67bdfca9cebf95ebe3854329e1e266aff10ab26f2

Observation 4208efd6-d86f-46c2-bdd4-883273eb30c3 · outbound

This paper cites AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.242137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.242137Z digest=sha256:290a491f90ecb2eb35f75e9f46cf87d665db1b3b964063a632b24270f411fe48

Observation 3a762ebc-9308-452a-a4c4-4837d38c2ce6 · outbound

This paper cites GUICourse: From General Vision Language Models to Versatile GUI Agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior GUICourse: From General Vision Language Models to Versatile GUI Agents

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.244906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.244906Z digest=sha256:fc7e7cf700d1d4d268ed1e12b34359fd2730a13521ad1fad0953ce488d8b0776

Observation a2784a31-86e4-4af1-a7b2-eb7b8a04bc52 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.247710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.247710Z digest=sha256:5b1012b91207a7d487047c46e8881394746c108e4929407ee48499d71f385fe9

Observation f9ef270f-4b9f-4abc-bc50-e19ec0d7eab8 · outbound

This paper cites SeeClick: Harnessing GUI grounding for advanced visual GUI agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior SeeClick: Harnessing GUI grounding for advanced visual GUI agents

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.250501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.250501Z digest=sha256:95710099a95ba958868c39f693150ea2493af54304d5a544241fa2be24c36ebe

Observation c376acd6-38ad-43a9-9dcd-c7b921019975 · outbound

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

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.253545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.253545Z digest=sha256:ff387cb117e99a8ed152555afee5a35b763c0504f767b88fad12e1a589fe38dd

Observation 3cfc651e-aab2-4d00-abe2-b2c5b951a3aa · outbound

This paper cites Navigating the digital world as humans do: Universal visual grounding for GUI agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Navigating the digital world as humans do: Universal visual grounding for GUI agents

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.256541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.256541Z digest=sha256:3e6103b5948b3e8445163f613491babf42a999a9a92464031b35264bf84844d1

Observation 1d10fcaf-3ad1-4387-98af-58649a7d385e · outbound

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

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.259113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.259113Z digest=sha256:bfc8751793bd132cfd9bdc8a7035df8dca0014a8e2556689c3514de20a4d44d0

Observation 2cfeaf0c-06a9-4a69-af84-d24806c342aa · outbound

This paper cites Cogagent: A visual language model for gui agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Cogagent: A visual language model for gui agents

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.261876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.261876Z digest=sha256:1085ee664fe0395053eaf23a61b1490156ba868e0c773b6d20a4da374c95ce6b

Observation 1dfd6497-3108-4fe0-b950-2f1dda5ab4b0 · outbound

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

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.264588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.264588Z digest=sha256:4f6134128ac9f65c8926104e76ffebb89ede4dce04f4a502223d1432bc0454eb

Observation 74a49541-9d5f-47ec-98c9-71751ca27525 · outbound

This paper cites GPT-4o System Card.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior GPT-4o System Card

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.267283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.267283Z digest=sha256:d06ecdae84e07cb29cf168e39ea4cbd3e6be0292ee918d8eeb97968f1fb86ca0

Observation 93c9c223-7613-453d-a8b8-876104977566 · outbound

This paper cites On the effects of data scale on ui control agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior On the effects of data scale on ui control agents

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.270122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.270122Z digest=sha256:41f47debb60138e0c83bc96f98dfa2cde46de7e6702379bc4cd726cf6909eb34

Observation e3e2b15d-84e6-4a17-92de-af98fafd2bb7 · outbound

This paper cites Appagent v2: Advanced agent for flexible mobile interactions.arXiv preprint arXiv:2408.11824, 2024.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Appagent v2: Advanced agent for flexible mobile interactions.arXiv preprint arXiv:2408.11824, 2024

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.272656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.272656Z digest=sha256:33e2de02526ad63454c3f9b3d81b5f36f63d32b9899f94f7c64cd7558ec311cd

Observation b97e3281-bee6-4fdf-952e-32a1f997fa7b · outbound

This paper cites Widget captioning: Generating natural language description for mobile user interface elements.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Widget captioning: Generating natural language description for mobile user interface elements

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.275117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.275117Z digest=sha256:319f689d71e88d9e0fa8ffd7ee7b9f564055acfea7ac3c74c15c157faec8e3ed

Observation f25c6af6-1b46-4286-b7ea-a4562b56b62b · outbound

This paper cites InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.277595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.277595Z digest=sha256:9901553fb14ddacad7ad0e0446f3aaa09f39d2e0f7482a4f6d3cd9ad26661df5

Observation d89678ae-eefd-4deb-9f6e-abbf051c7e48 · outbound

This paper cites Visual-RFT: Visual Reinforcement Fine-Tuning.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.280318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.280318Z digest=sha256:b0ed2b28381c3118cdc84e6be43e1e4f383f45f808cef26c3ea2870eae4e74bb

Observation 1701046f-59fb-4883-a5d4-4eefed5cf5a9 · outbound

This paper cites Decoupled weight decay regularization.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Decoupled weight decay regularization

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.282991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.282991Z digest=sha256:5cd5d587d1606e04f024a900230b333a9b76eedf157adc844644d8de3a98f296

Observation f487c515-d647-4c59-a909-370a7a20cc74 · outbound

This paper cites GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.285873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.285873Z digest=sha256:3d96f7e8e6361a5b78404eb2b50eb64c43edb227bd5edb78d531b2c3b7123927

Observation 8bc6b6ca-65f7-4c92-b223-1f4db83ad15c · outbound

This paper cites Omniparser for pure vision based gui agent, 2024.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Omniparser for pure vision based gui agent, 2024

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.288587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.288587Z digest=sha256:40b6554669ded9f3caa4bb6dc9b47f81ec0fd32fd2dfe14012ed510cbfb50a1b

Observation c72e5a7d-0281-4ce8-89d6-14232ee79777 · outbound

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

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.291084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.291084Z digest=sha256:60140d7dec70e351fba7cb87f0ec62559f3563918ce4ba80cf3250bd881f7703

Observation e9372d0b-e97d-4181-a8c6-110e7bcc2a6c · outbound

This paper cites UI-TARS: Pioneering Automated GUI Interaction with Native Agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.293798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.293798Z digest=sha256:2bb1f107e1f60c8d477522b6a7ec74e95c891d8133798c118936361ca189b7db

Observation 8a8cc552-4d5c-4cae-92ab-250a9500e1bf · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Direct preference optimization: Your language model is secretly a reward model

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.296683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.296683Z digest=sha256:e913e8d0675575b44d4cd9e2146d2d0a4f0785b916e99e7ed0d709e14b73917f

Observation 1158c803-3fcf-4e3f-9434-8964ccdea59f · outbound

This paper cites AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.300086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.300086Z digest=sha256:f651d9a58df2e74d35458510fe4a0bfb340ca7181d1efb4ee79c81f6768d8f0f

Observation 01914f21-bc38-4847-9253-8d953065e065 · outbound

This paper cites An- droidinthewild: A large-scale dataset for android device control.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior An- droidinthewild: A large-scale dataset for android device control

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.302871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.302871Z digest=sha256:5ff7424cc21a5f99cbf32a3df449a76ffe3d4532c25d04599053be1a86a775d4

Observation ee13e21a-3f3f-4610-bb88-f10be64f2f44 · outbound

This paper cites Rethinking Reflection in Pre-Training.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Rethinking Reflection in Pre-Training

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.305470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.305470Z digest=sha256:aedabf9400e4e7e95c4d6d409f3e4a638b6132aa50a4d51bd6e960fc65608173

Observation a27ba966-dee0-4cae-8dff-e83ace18a5bb · outbound

This paper cites Learning to summarize with human feedback.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Learning to summarize with human feedback

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.308328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.308328Z digest=sha256:16e157bc798f39cd1de224ebe48a5ff62789f9286a8a45708571a1ae4b6f682a

Observation 0625a43c-daf4-4606-bcce-b0cdb6c6fa2f · outbound

This paper cites OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.311393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.311393Z digest=sha256:88a09fca1fab1e725c57cff392658df35c52bec758a607c01ca05248618337ea

Observation eb83ec30-2fb5-4205-99dd-1e940ad2ae93 · outbound

This paper cites Towards Better Semantic Understanding of Mobile Interfaces.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Towards Better Semantic Understanding of Mobile Interfaces

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.314614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.314614Z digest=sha256:865f7c53ba0622ad46d36fe4aa849906f86ed7fe2467f5ffed8fd80085112a02

Observation ecb63aa9-03a0-4e41-8d16-73e560c398b3 · outbound

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

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Gemini: A Family of Highly Capable Multimodal Models

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.317580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.317580Z digest=sha256:2a8114f847a124fbce30f356ef09572bc8fedcf020859c87c8531396475c6544

Observation 87645fa8-3157-41e4-8302-a8562cd6e06d · outbound

This paper cites Mobile-agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Mobile-agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.320381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.320381Z digest=sha256:a68544e966cc48a2eb2606b1e4b9d6bb38e2a2acea6ba394cd94a7adb7f74f75

Observation f117333c-5809-45c1-abb6-953775bc1836 · outbound

This paper cites Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.323535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.323535Z digest=sha256:de85f70e6ad8c8f588d7fcd2cf4a963d219910d5700ee3e4f101e0877fe7b30c

Observation 4c4203f8-6dcc-4a84-815d-e446b0a0fe6c · outbound

This paper cites Distrl: An asynchronous distributed reinforcement learning framework for on-device control agent.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Distrl: An asynchronous distributed reinforcement learning framework for on-device control agent

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.326219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.326219Z digest=sha256:82fafb8a1251b5cd5a91e5d3f525b62463820a68d2e009592cf729f500887aa0

Observation b9f57cee-9695-40ea-b683-f0d9f954d584 · outbound

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

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Chain-of-thought prompting elicits reasoning in large language models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.329083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.329083Z digest=sha256:cda3c64f1063810a3de12ae34858d0ee4f6306bc4483f1773527d5b01e57970a

Observation 22fc73e2-1e44-4bb1-a78f-de13adbb133f · outbound

This paper cites OS-ATLAS: Foundation action model for generalist GUI agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior OS-ATLAS: Foundation action model for generalist GUI agents

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.331816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.331816Z digest=sha256:3878e116543c9b81136cbba36d4d8dc22a304d39d665395a95cbf459ff599e3a

Observation 60f5e96d-bf52-4690-8688-f0c863f9efcb · outbound

This paper cites Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.334325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.334325Z digest=sha256:91258fbd877ed94076cdd640db311811e22a8f2e792f658d4027e744cf33203a

Observation 0884fe93-ac0d-489c-998e-8dcc643f07df · outbound

This paper cites Aria-UI: Visual Grounding for GUI Instructions.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Aria-UI: Visual Grounding for GUI Instructions

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.337178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.337178Z digest=sha256:2568d71376447e2799c9644a39e394b2cc063dd1fe34b2f04b4239bdeb35601f

Observation d59d73ec-211b-422c-ae89-d79615709d78 · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.NeurIPS, 2023.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Tree of thoughts: Deliberate problem solving with large language models.NeurIPS, 2023

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.340020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.340020Z digest=sha256:f82b196c41af0c55c26ba9ffba9dcbba8ce55801ef189d9a7d6e4f63ddea37a0

Observation ac87e958-e46c-4106-8316-d91bf4eced68 · outbound

This paper cites LIMO: Less is More for Reasoning.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior LIMO: Less is More for Reasoning

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.342561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.342561Z digest=sha256:1612c3fd690eb9f963336dce2831a6fea17c8e0110bdb31b16f5b8550d7cafab

Observation 971c2c55-ff7d-4cd7-b58c-342350fbe477 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.345287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.345287Z digest=sha256:72c4caa7a9bfdf0a9a8a7f1f996b3d627be1a95c029ab9d5a7d3c67aaa6dcc7e

Observation 142b9064-cf0a-4cdc-8c7f-2c39389ef7b3 · outbound

This paper cites AppAgent: Multimodal Agents as Smartphone Users.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior AppAgent: Multimodal Agents as Smartphone Users

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.348013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.348013Z digest=sha256:46d18903a6615fca00ff914fc3ebad79c7e4625a52244933d31b86bad68b0b3c

Observation a1d52607-bcb8-40a9-b839-0ce8998c5386 · outbound

This paper cites Android in the zoo: Chain-of-action-thought for GUI agents.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Android in the zoo: Chain-of-action-thought for GUI agents

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.351103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.351103Z digest=sha256:e16a520966b9f69a217a2df4f725bf7784e9ac857f5bf09356bfb62eefba7463

Observation 16589979-3770-4fe5-a319-7e9b79570237 · outbound

This paper cites Breaking the Data Barrier -- Building GUI Agents Through Task Generalization.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.354138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.354138Z digest=sha256:b9d71db30ce0e67c0a851a5ca548ddfc5c71759922a40453ae597ca96450cfd9

Observation 4a73a914-c334-4cf9-97bc-ecbe085b42ca · outbound

This paper cites Gpt-4v(ision) is a generalist web agent, if grounded.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Gpt-4v(ision) is a generalist web agent, if grounded

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.356970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.356970Z digest=sha256:1ab18e908d740fb58f46a4d7c45b312f2e7fe35e801a8b1a35e9fed27e42adda

Observation 49cb0657-4e38-4676-b54e-3acf8100c50d · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.359646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.359646Z digest=sha256:e6446947f08273020c79f220787a08141f4c84434ca566b906aff34acdb78078

Observation e5cf40ba-82fe-428a-8fa0-75566c8db646 · outbound

This paper cites To obtain the failed attempts in training data, we first train a GUI-Pretrain model with the three target datasets for this task excluded.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior To obtain the failed attempts in training data, we first train a GUI-Pretrain model with the three target datasets for this task excluded

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.362940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.362940Z digest=sha256:2c19edb902a19803702c4e38acb6eb5b70ec9b11adcd9137dc1463b0465a53c0

Observation e19c670b-e00a-450a-b4a5-1e8ae7023e0f · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.365899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.365899Z digest=sha256:8dd92952e1f82131a1a0641e7491cd596fc194e0850580817a9907f9d6dbb3ec

Observation d7e513a8-8226-4944-b83c-bc589c308cb9 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T05:25:59.368745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:25:59.368745Z digest=sha256:a9f2b5f292939f87d7684cd08e3e744a401a5e18a37e4abe4e7c7bfc543fc8a9

Observation 2c2e98c8-6cf7-402b-aa2e-f6d0fd9eda24 · outbound

This paper cites new purpose.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior new purpose

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.490403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.371845Z digest=sha256:2647e362f16b3ed7363706c24214eb13cc0d78d3dff467e8c0927894c24dbb91

Observation fc5d650c-b64d-4d91-87ae-b0b909cc8880 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 58

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.481588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.375273Z digest=sha256:beea257d33f71641faf963929636c004fd54b91a38b7d476f4c7f7b3d707eb1b

Observation b65d97cf-90b3-4f17-9dd2-3bf576299fd3 · outbound

This paper cites The click point is highlighted using a red dot in the current screenshot and the scroll positions are visualized using a red arrow in the current screenshot.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior The click point is highlighted using a red dot in the current screenshot and the scroll positions are visualized using a red arrow in the current screenshot

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.446758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.387486Z digest=sha256:6f35feeb2f2c5ef71cc07f991214986fb7531eb7920c4560bb58d13076317126

Observation 96c5c805-057b-4b1e-a9be-a41d189d3f55 · outbound

This paper cites Ignore the following if not.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Ignore the following if not

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.437902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.390016Z digest=sha256:33cebff87f5cd673c9fdfd4d674171034bdb89258a73c8fdb8f6153a3b730a66

Observation 0cc88904-c2bf-4047-a9f3-5f14cf0c8aeb · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 64

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.428965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.392672Z digest=sha256:4f1b5c6c16b4bf23bda1e9b7e432a075dea8a9ea2947888d50c3423c8c0685ca

Observation 725e6939-3689-4aa1-b957-b46d848810fb · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 65

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.420510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.395165Z digest=sha256:114cda878fb95b35090d2610772bd6e423e5a83d22d21fc6a7d18002d80b0391

Observation 2d3445ed-de7e-4346-ba82-986b670a7525 · outbound

This paper cites Task Feasibility.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Task Feasibility

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.411939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.397590Z digest=sha256:ca5016298bd1f2a63949c5ce0ab66d7beb3daa3c6ed62521c6ea5e45705f6035

Observation 6108677d-bfee-4dda-ae36-2da7944459c9 · outbound

This paper cites Empty if it is the first step.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Empty if it is the first step

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.394338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.402877Z digest=sha256:23e54c3443d801e7b686ba573d3032cdb69b474e2b685ad5c0c4b09220fcf61a

Observation 7f51e527-f9df-4c7d-9ba9-e929f4158fc6 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 69

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.384259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.405229Z digest=sha256:77011bfa954ed1c2a5f45bcef224bb686e384cdee8d6baf88e4e661e7870a2e6

Observation 53b081ad-5efc-4403-a432-6fcc8d701b83 · outbound

This paper cites The click point is highlighted using a red dot in the first screenshot.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior The click point is highlighted using a red dot in the first screenshot

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.367471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.410635Z digest=sha256:5668fa8095bb32c8646d5473615b47dd1b2cae9fb9d6dad2bc9840375ca1778c

Observation 943dcf83-5100-4c91-89c3-ae3481abcdfc · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 72

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.359493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.413568Z digest=sha256:b6a9bc026bd00af2cc7e09760b613dd8bf575fd021605dc17a936f843d7be27d

Observation 9a2e884e-ef86-4826-ba28-0e259def77f2 · outbound

This paper cites In the action thought, use first-person description, that is, using ’I’ instead of ’the user’ or ’the agent’.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior In the action thought, use first-person description, that is, using ’I’ instead of ’the user’ or ’the agent’

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.351726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.416946Z digest=sha256:4970371fc6315d3fc83690fab7b93595030c1e63066367a0a0de44a2482b6987

Observation 63df3110-e6cd-41fe-bbbb-c54f36554484 · outbound

This paper cites Action Thought.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Action Thought

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.343677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.420485Z digest=sha256:e0f1790a47c12b3f5f9791367880184a3cb4a97d007cb767efacb9e897970154

Observation 0835d1f3-7e34-43ca-bcac-78ad7683109d · outbound

This paper cites Empty if it is the first step.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Empty if it is the first step

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.336120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.423211Z digest=sha256:e524ef551ce43c12b4ef0999e3cf14443ed474919212e7cd2c36ea1889ab8694

Observation 1563eab4-90e5-499e-9df4-313f4f0880de · outbound

This paper cites Only the current screenshot is provided if it is the first step.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Only the current screenshot is provided if it is the first step

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.328273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.425980Z digest=sha256:5b5b0f21b852edebba29960f8642a807a201cfb160476d16841fe92c68dcde61

Observation d4d8cf7e-b5e0-4fcc-9bc2-c422985c981a · outbound

This paper cites In the action thought, use first-person description, that is, using ’I’ instead of ’the user’ or ’the agent’.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior In the action thought, use first-person description, that is, using ’I’ instead of ’the user’ or ’the agent’

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.319981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.428571Z digest=sha256:71eecfe7fa63e1745db2044cc5bdbaa7e6b78212be2ca87b23cd8bd4ae805668

Observation 36d95acc-2d6b-4038-ad99-959116c23abf · outbound

This paper cites Action Thought.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Action Thought

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.312031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.431447Z digest=sha256:aab962c10172c1eafff5998536cb3ccd8004de9fefcdd31f3f6bbfb02ec8f212

Observation e8206b88-3061-4a9b-890a-6a50c8df6f79 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 80

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.304365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.436498Z digest=sha256:8d7db583201bf4a4d497e718888432c4eb55e861976f570ca1a5e8cab803ab72

Observation db9d20a3-2fcc-48a4-a5bf-aee4dc46e607 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 81

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.375047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.438903Z digest=sha256:8a1fb44ee55bcfd4e723be0b844dca4903927fb3120c1bea3f8f6dede3a94097

Observation 2bbebc6b-ef9f-4723-86ba-29dc9bd72378 · outbound

This paper cites Updated Action Thought.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Updated Action Thought

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.288689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.443870Z digest=sha256:e4045f9806ab0a0153ff3d88de79ac013abbde38f01c2abfba2f7f6131002839

Observation 6f555a8d-de62-4c69-be75-bb3f821337c4 · outbound

This paper cites Empty if it is the first step.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Empty if it is the first step

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.472852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.446560Z digest=sha256:347cd0f6d254b9e9a56a9698c1c1b9d5d11d38a3cf9f32f8637f7c15269b20ef

Observation a9e60b80-6174-497a-a3ab-0c846fe890bd · outbound

This paper cites Empty if it is the last step.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Empty if it is the last step

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.464203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.449229Z digest=sha256:6ca43f5b7d7ffdb3e245424a39c30fd0885a87ac04546118afc51afd3b118df4

Observation 43d4ce1e-a475-4c40-b4d5-54180bc236d9 · outbound

This paper cites The click point is highlighted using a red dot in the current screenshot.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior The click point is highlighted using a red dot in the current screenshot

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.280593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.455668Z digest=sha256:6bc82753eca22ea23c9e18699c1855e9b7affaf03ad519f095fe2e2ffd243636

Observation be958478-103d-4b4a-8ef9-d2acb562784e · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 88

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.272788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.459208Z digest=sha256:50b767e0568a9a2d91572b71b26ae870072a43b143170ef9800775d91bab655b

Observation 08b82836-6693-4639-8295-9334f41e22b0 · outbound

This paper cites The user will probably realize the mistake when seeing the execution of this action.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior The user will probably realize the mistake when seeing the execution of this action

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.265182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.461891Z digest=sha256:fd8464dad9c77c33f65b5e2648be7dfc9abcbd49bc1c09cfefafd9537d4b8fb2

Observation bedeb272-8fd3-4163-a807-fb0a21b1e3db · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 90

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.257113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.464346Z digest=sha256:a62468cd6e6aa7b92951f664c05cff0b9708ac92562b75d7b880f4d945c2487b

Observation 65dc8f8b-6acc-4237-9985-d37fdccfe199 · outbound

This paper cites Ignore the following if not.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Ignore the following if not

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.249633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.466995Z digest=sha256:53d706fd0f1175a291c7e010835aa901214a8665f7f9af189a405d9570ce25f2

Observation 5a2cb42a-caec-4351-bae7-2e1cea485c01 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 92

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.241981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.469454Z digest=sha256:30f5fe54980012fc68780c3997cf3871fd563b076dd3f00e62dc8feede25e759

Observation 0d3566cc-36a4-4b43-b6d4-efc16b7c6fc5 · outbound

This paper cites Task Feasibility.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Task Feasibility

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.233458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.472223Z digest=sha256:272663b0f863849e83b3ff520f4f7998b4a98f487df07317aef6612b500f7e1a

Observation 030d2de2-aa5d-4a43-94c4-33c48f99ef79 · outbound

This paper cites Error Action Analysis: An analysis from an expert explaining why the previous action is incorrect and why it might happen.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Error Action Analysis: An analysis from an expert explaining why the previous action is incorrect and why it might happen

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.225923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.477378Z digest=sha256:586c4340de126d6ed852fa7c3c7ee6957c3146709ebd26edec2a340a744472b4

Observation d2f7ca81-39a4-4678-8f62-d2109b5bc510 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 96

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.296523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.479839Z digest=sha256:aa0dc5183dc972c6b8a47795d770f423c691b9d2dcc1f7204842816fdd36051a

Observation 0290d782-59a8-44b1-866f-41f2634dc6b5 · outbound

This paper cites Updated Action Thought.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Updated Action Thought

Reference 97

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.217635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.482529Z digest=sha256:87a7c56f8f1074f02eff2ceca66eb7e92a12e43177f130374ed2fb13ae12ab4d

Observation 7ebc3ed9-d99f-428a-8134-9e4f95491328 · outbound

This paper cites 2: Task Guidance: An overall description about how to **correctly** complete this task as a reference.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior 2: Task Guidance: An overall description about how to **correctly** complete this task as a reference

Reference 98

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.209905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.485242Z digest=sha256:d185b4b77b0c53ee86a72b7fda5555b38c0003f715bcfd03e6993f36f430fe99

Observation 7b315fed-acdd-4298-a5c2-a1ca0fee6455 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 99

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.201621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.487945Z digest=sha256:961a3d6ab4f18459cc0a813d4136d5ccbe71780758c602dd34a9d8060994b385

Observation 4bc68814-dcf2-4884-8282-11a896757e08 · outbound

This paper cites Empty if there is no answer action.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Empty if there is no answer action

Reference 100

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.193826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.490501Z digest=sha256:eac620825d1b46341fa0ea5561650851014b645a090b425ea90f2f0f00b5e010

Observation 6cfe21b7-6502-44aa-9636-850f7650eb99 · outbound

This paper cites The status is either Task Complete or Task Impossible.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior The status is either Task Complete or Task Impossible

Reference 101

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.186096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.493001Z digest=sha256:a94ffc01108c3c6ba27074f3ffcad3d1ab2dc0bf1b2812e3f1b4529dc65c4ba4

Observation 1290f7da-d1d8-41d6-bf9b-5878d120d1d2 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 102

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.178274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.495582Z digest=sha256:7d5d4dc51e3f9c8f8c610dd8b3371aac5197e8e59df9214877b0b7be5bae00f9

Observation 983cc63b-a02d-4a29-acb6-b3cbdedaac93 · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 103

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.169914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.497962Z digest=sha256:fbdd34ed7cb94f8bf26515cb773fa25ff1cd9dd25050b0bcfcf08b4cec81a077

Observation 6794327a-dd9d-49ef-82f8-d66c640d18e4 · outbound

This paper cites Task Analysis.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Task Analysis

Reference 104

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.161430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.500488Z digest=sha256:8b081e3e1598a5234311366e28db42358be3d630bd102be4c9a2e6227ed4e48c

Observation d59513da-a6ca-402c-a30b-f6ac98f603ee · outbound

This paper cites 3: GT Answer: The ground truth answer for this task.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior 3: GT Answer: The ground truth answer for this task

Reference 106

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.153055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.505373Z digest=sha256:7f79daf414d2018ccc02e3db8f5baaa8bf4bcfa23e925bb8e9e8ee33e571b762

Observation 4563e5b1-9d4c-4df7-ab57-f4af3833b990 · outbound

This paper cites The click point is highlighted using a red dot in the current screenshot and the scroll positions are visualized using a red arrow in the current screenshot.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior The click point is highlighted using a red dot in the current screenshot and the scroll positions are visualized using a red arrow in the current screenshot

Reference 109

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.136320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.512691Z digest=sha256:ba33cce8b9680a0519366f5410cd2cc3a2c96a6c4b2640008d01a1b64ff42490

Observation c576c861-b605-49eb-8044-ffbcccc84e37 · outbound

This paper cites Reasoning.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Reasoning

Reference 112

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.109682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.520145Z digest=sha256:ea4f45671d0dcd4891188893e88e9170fa8dc7fb844b6d6624a5b9529d2896ba

Observation ceb70bbb-2fd7-4144-bf64-8924f98713ba · outbound

This paper cites an unresolved cited work.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior Unresolved cited work

Reference 113

Resolution
unresolved
raw_fallback, observed 2026-08-07T05:26:00.403385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.522618Z digest=sha256:e38beb20d44ea12a296ff0ea7155765123586de99a4bae02eb928e8cff2e879a

Observation cef696db-e2e1-41dd-95a7-dd00139b9c22 · outbound

This paper cites 32 3: GT Answer: The ground truth answer for this task.

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior 32 3: GT Answer: The ground truth answer for this task

Reference 114

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T05:26:00.100400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-07T05:25:59.525256Z digest=sha256:eac1515230368a26e97a4f59aed0aa19f3f9df430a2fdb8940126f65f464bd8e

Pith citing papers

Observation 47fb7f25-87e9-421c-907e-0ee450668fb9 · inbound

UIPress: Bringing Optical Token Compression to UI-to-Code Generation cites this paper.

UIPress: Bringing Optical Token Compression to UI-to-Code Generation GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Reference 59

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:00:58.945835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-10T17:21:32.024105Z digest=sha256:9abb02916e380474e18f6566445380e5485c834500ce51c53c01b1aa5f9844ce

Observation 993594b4-3bce-4036-85ec-0884401756fc · inbound

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability cites this paper.

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Reference 84

Resolution
verified exact
arxiv_id, observed 2026-05-11T04:35:57.109936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-11T01:15:19.239355Z digest=sha256:53b53235004de8e78a39097a9cbde98e5f450cc41277061b18ca9e94b8516c6b

Observation 1ede78c2-33dc-454e-8de6-e27248e329a5 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Reference 51

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T20:56:13.308915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-06-28T17:38:50.313305Z digest=sha256:8a501e5dad183db8bdfa1ffe8beddc895ec1d793d2e681bfc16a65156eecf214

Observation 8ba0ea85-ba72-4f89-a90c-91e1cd7f1747 · inbound

A History-Aware Visually Grounded Critic for Computer Use Agents cites this paper.

A History-Aware Visually Grounded Critic for Computer Use Agents GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Reference 25

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T05:27:39.586276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-06-27T13:20:32.432002Z digest=sha256:3395f4f3260119565ccc6ed0593a1d9a65ae606e65ccf28d3eff0d9ebe386879

Observation 79dd7489-a0ec-4678-b154-9b60293f307b · inbound

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application cites this paper.

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Reference 287

Resolution
verified exact
arxiv_id, observed 2026-06-27T09:50:48.390488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-06-27T09:46:30.702256Z digest=sha256:2fa1cc24c4b423336e9dda306fb6e0f60e97ed8466cfc898dded4cb04d286ea4