Pith. sign in

Paper Citation Record · LEDGER

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

As of 19 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 10 inbound Pith citation observations for arXiv:2505.21496.

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

pith.paper-citation-record.v1
2505.21496 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:34:16.540169Z

measured 55 of 55 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 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T20:19:16.086843Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T05:17:40.282692Z

Reference resolution

45 of 45 outbound references displayed

  • verified exact0
  • verified fuzzy2
  • unresolved43
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 227e2ae3-3a85-4962-9ffa-e7834f866702 · outbound

This paper cites Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.202353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.202353Z digest=sha256:0292e76fbac767fc8c1a85a504d2447d021b467bacab646f1e29eeaa7d07cad8

Observation a2f36f7f-c2e9-4ecd-b9a8-939e3a2ed610 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.249449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.249449Z digest=sha256:d041caeea478344c308fc0ceebfb75bb54ff02a7e58aec304dc3a7414b2f6c94

Observation 7465ed76-0ae9-4e79-ae52-f65a0c47afa5 · outbound

This paper cites Qwen2.5-VL Technical Report.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Qwen2.5-VL Technical Report

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.316549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.316549Z digest=sha256:d87ef452c94a3896339a78369c6729627d3e7163d4d9e3023f971e79fa5c6013

Observation e7f68e8e-48ee-48c7-b024-8ce6c8907cfa · outbound

This paper cites A survey of monte carlo tree search methods.IEEE Transactions on Computational Intelligence and AI in games, 4(1):1–43, 2012.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents A survey of monte carlo tree search methods.IEEE Transactions on Computational Intelligence and AI in games, 4(1):1–43, 2012

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.379422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.379422Z digest=sha256:f62ab625295b051c080ed071f2ed6d93f1a22f4dcc4db51fadca89e334b4e4fe

Observation 9f0b76e8-ea5d-4239-af90-8675f023a612 · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.433269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.433269Z digest=sha256:db6b436b9439d3ee6441c4a82fbf500ac957b5d0b79a60abf7b273d4ccac528a

Observation 31233573-e7a7-4112-8222-849a623d1057 · outbound

This paper cites A3: Android agent arena for mobile gui agents.arXiv preprint arXiv:2501.01149, 2025.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents A3: Android agent arena for mobile gui agents.arXiv preprint arXiv:2501.01149, 2025

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.506033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.506033Z digest=sha256:960d0d14972cb83be257170126d1a1a901f1ddf8d1cf9424aa51fdf0be07baa4

Observation 0d1cd788-394a-43d5-bbad-e5da891f9fc6 · outbound

This paper cites AlphaMath Almost Zero: Process Supervision without Process.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents AlphaMath Almost Zero: Process Supervision without Process

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.576689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.576689Z digest=sha256:e6ce569c0389290b9db71e32493beb84d3c0fe442a7c79e8aba46f687a56161a

Observation f8d6c2ca-21f7-4c57-a9b2-d1fed7883993 · outbound

This paper cites SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.653482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.653482Z digest=sha256:6bc2820e8554aba32b9385fa88ce535c2d7fbaa1780085a57e4329c5c9febdf8

Observation f779bc17-e800-4b2d-bdc9-34e5539ba275 · outbound

This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.734899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.734899Z digest=sha256:4ba5d5ee368a3c77aa4924ba47dd4d1b89715c8fcf835cffed65c50b1dc761f5

Observation ca5dbac5-7c7b-4248-94c3-41f5904e5db8 · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.797680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.797680Z digest=sha256:4062b524df4115025a6a814c66b3f85ea7387ed692d7d71feaf0f60b3634ba51

Observation 5291f4ed-3582-48b4-a0a5-fe1bc8e8c58c · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Cogagent: A visual language model for gui agents

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.869363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.869363Z digest=sha256:0c601cedb6939cf6d08be6a3a89777df24fee8133418a6df19e30432d2592d7c

Observation ede2a85a-43d5-41a2-8f87-252065a26fc8 · outbound

This paper cites 3D-LLM: Injecting the 3D World into Large Language Models.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents 3D-LLM: Injecting the 3D World into Large Language Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:12.942509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:12.942509Z digest=sha256:41f738cf47b44d0d1720fae75dd1f82faa1ad557302101541d7caabad40de71f

Observation 2311d38f-86cf-4f67-87ed-853bfaf5705d · outbound

This paper cites On the effects of data scale on computer control agents.arXiv e-prints, pages arXiv–2406, 2024.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents On the effects of data scale on computer control agents.arXiv e-prints, pages arXiv–2406, 2024

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:34:17.722438Z

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=2026-08-07T13:34:13.035312Z digest=sha256:55bb8edee5e7824f73cf69e26a98f6880399aa72d0cba7d9687f6e27b5722371

Observation 887cdd4c-5205-4652-a939-da5b5e711103 · outbound

This paper cites Let’s verify step by step.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Let’s verify step by step

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.140041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.140041Z digest=sha256:6862cdef157f3c6469a453c24f5ae640d1af5beb7f06799ea60b24316ccda40c

Observation 92a97f96-647a-453c-a8a7-13773936f429 · outbound

This paper cites SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.235887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.235887Z digest=sha256:fc5bbacf809ed3724d3838b888f4d9924896a213db65def7d5ea79627819f351

Observation 292911e5-8523-4bf0-a20d-6ab532f11507 · outbound

This paper cites DeepSeek-V3 Technical Report.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents DeepSeek-V3 Technical Report

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.339552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.339552Z digest=sha256:f991ac162a4b2216baff3995e33af280d6e205e9d0450177b57964b97d5d39af

Observation c5cd0a30-8150-4219-9a2a-8804e503146f · outbound

This paper cites InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.481997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.481997Z digest=sha256:cd7021d773cd5129d37fc4eaf47e44383a686d31d70ceb32c71d5f3a858a3a7f

Observation 4c982ce9-de55-414f-b99b-e78a0d8b3a49 · outbound

This paper cites UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.620018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.620018Z digest=sha256:76f2853c9e5430fe1963aa8cc1c00a9a0aa52cf07209a03d414083ae9ccc3fc6

Observation 0f33a703-4705-4b47-8a72-5a2f45a5edd8 · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.755616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.755616Z digest=sha256:00f6fd43337bdf61895b863eee03ddbadb0793575676337933e1ddebc466bc4a

Observation c2f9b3b7-b026-492d-aae0-ca092bc084fc · outbound

This paper cites Chatgpt.https://chat.openai.com, 2023.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Chatgpt.https://chat.openai.com, 2023

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.862753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.862753Z digest=sha256:32faeada7b221160d847bdd16495d147a80a2100837be767b593cb86cc4dfa76

Observation 8f64ac00-d58b-4ca5-b8a6-74c2aa79dc80 · outbound

This paper cites GPT-4 Technical Report.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents GPT-4 Technical Report

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:13.981674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:13.981674Z digest=sha256:5d431b4c1265f415a317ac2ecfaf57453b99625b5f76bd47b3fb9cac331ca667

Observation a4ea2b57-ebf4-42ff-9979-5c8891bc4380 · outbound

This paper cites Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:14.113020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:14.113020Z digest=sha256:5476b072d3409e8d21b8be4b088a8e04cb5d042f6c91cb1c8809dbc3e22701b4

Observation 92256e3c-d1ad-4ea4-a686-baab33ea19aa · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:14.257156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:14.257156Z digest=sha256:3c5e9fdaeab416326a8b8db5a3e90623847ebac0cbb12accd31e2f88824ccfd0

Observation 18e99542-9edb-404b-922c-7bd8fd6b195b · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:14.409660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:14.409660Z digest=sha256:8895930deeb1601269ee86fece07b5e36701fb9d169bcb3cc265fe20f41eb657

Observation 4299b27c-2464-471b-8631-fd47de7faa97 · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:14.554994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:14.554994Z digest=sha256:082d36d26a1ee9857696243e9c5dfa55fd2384d8e87ea5ce7c285e6316e7f9d4

Observation 0b45da9d-dea5-4d83-a679-ceb0e656aa83 · outbound

This paper cites Mas- tering the game of go with deep neural networks and tree search.nature, 529(7587):484–489, 2016.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Mas- tering the game of go with deep neural networks and tree search.nature, 529(7587):484–489, 2016

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:14.699428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:14.699428Z digest=sha256:68c4877b2c5dfac27c26458fffe01bfdb83d121517a66a03b30963377c7caa5d

Observation 16db5226-a409-4b9c-864a-bf6255dbe2ed · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:14.819538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:14.819538Z digest=sha256:bf472d04be8ae3f2a7f23fd3c0c1c5048380c04d6ed093a8c832e4ea52139f3f

Observation 7297932f-4faf-4bc3-ab0f-fd3a169a502c · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:14.968525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:14.968525Z digest=sha256:39bdc422c64982fa56b072648ddffc3a649fd6688290daac18e082a42506e790

Observation 44e31cf1-f544-4aeb-a2eb-5ddf837cb190 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Solving math word problems with process- and outcome-based feedback

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.089504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.089504Z digest=sha256:2e7b88ea1c995a6c0a9616981a47934fa7ac939816ac81320667106da54eeddc

Observation fe1316b3-e451-4395-ae3c-764650b0e91a · outbound

This paper cites Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.163897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.163897Z digest=sha256:d426b56d9ee6778e03297d1b76e1ddb59d643d49ca17e5fd872b9905431e3976

Observation bbef74c7-fff6-4cc0-980b-e343c0d65e40 · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.236161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.236161Z digest=sha256:cad3f171988014e4a7ae466521ecede517037c79e3c2f4fb20c451fbbd4d077d

Observation def6758d-5dbf-4975-9f7d-8f9d65e82240 · outbound

This paper cites Mathcoder-VL: Bridging vision and code for enhanced multimodal mathematical reasoning.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Mathcoder-VL: Bridging vision and code for enhanced multimodal mathematical reasoning

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:34:17.521569Z

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=2026-08-07T13:34:15.316016Z digest=sha256:b201f552f89b96d1ac934a24bbe2e00f533d478781870e65f97e1b97383743e7

Observation 1df33d67-42ef-4230-8368-26f8a79366c6 · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.423628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.423628Z digest=sha256:9a0ca6a7501721032c13b8fc110a1fda1e063f419b573c5bfc5a0b76abba69e0

Observation 1aa3ba3e-bc83-4e45-923a-36e8737cec09 · outbound

This paper cites VisualPRM: An Effective Process Reward Model for Multimodal Reasoning.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents VisualPRM: An Effective Process Reward Model for Multimodal Reasoning

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.560978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.560978Z digest=sha256:4d4bd0ff7c49c88be2a84b4b0dbc405130629a307449276c9f07737499fb859e

Observation 8af82fd7-ea28-4370-a825-150a1c1f3d2e · outbound

This paper cites Unified Reward Model for Multimodal Understanding and Generation.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Unified Reward Model for Multimodal Understanding and Generation

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.647874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.647874Z digest=sha256:e6a9c47c2005064349c3c5707b4e255d4661bc74a2d0b750dfb296068387f15b

Observation 8fb54bdf-7891-4fab-8e5a-d249069a88b9 · outbound

This paper cites OS-ATLAS: A Foundation Action Model for Generalist GUI Agents.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.744658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.744658Z digest=sha256:6e2d8c13e83593f32256ef8e63d629a65748bbf071dfa720d6cb1e4e2d7fa295

Observation cf9fdf4f-a4ba-4e57-b9c9-f3686dbf2bf3 · outbound

This paper cites AgentRM: Enhancing Agent Generalization with Reward Modeling.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents AgentRM: Enhancing Agent Generalization with Reward Modeling

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.862250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.862250Z digest=sha256:9748ab2bd51e265e6effa389c8515fa872e4685c1ae4d28465a5d4d22e2c5c7d

Observation af4cb082-3624-408f-8885-41b813c97ed9 · outbound

This paper cites AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:15.971321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:15.971321Z digest=sha256:fb76be2a0af2c43c94cd360a050b310fce2220942b153d57e21c8a3fd0436dda

Observation 3725fa04-4eae-44f7-9e8d-9e1c688ce59e · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:16.052993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:16.052993Z digest=sha256:a3e0951cfd71479fc4c4e25dc1af9788c2343bcfd959568af6f447d6c6e0ebce

Observation c048bd41-ef28-4f99-888c-ac0ddaf58a90 · outbound

This paper cites OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:16.142382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:16.142382Z digest=sha256:ecec91ba2dc8ceb6d265ecf614cf4c2f58f39b3f1cbba8d1a39df8cb368abde8

Observation 0390a426-2071-44cc-81f4-329ffa836446 · outbound

This paper cites Free Process Rewards without Process Labels.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Free Process Rewards without Process Labels

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:16.228199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:16.228199Z digest=sha256:8c6811c443d4d2f2ad22e99c6c7454813a06f1fe4f1ff2c1b46848aa68ee39bf

Observation 38988312-0153-4080-8c93-3efae3d66d08 · outbound

This paper cites InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:16.325870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:16.325870Z digest=sha256:bec3e8032ef8ff7d25e70442c0eaa62e584d973a29884cf90cb99316609e5474

Observation c7a15394-1998-4c38-84fa-f5a389b6a23f · outbound

This paper cites Appagent: Multimodal agents as smartphone users.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Appagent: Multimodal agents as smartphone users

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:16.413731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:16.413731Z digest=sha256:9fc892d7c8b2211b7cdd7c08efc91b53451785ae9bf42ebb78d0115c8cca7085

Observation 289121d4-a544-4f0d-92f6-41ef672b1dfa · outbound

This paper cites Generative Verifiers: Reward Modeling as Next-Token Prediction.

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Generative Verifiers: Reward Modeling as Next-Token Prediction

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:16.465747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:16.465747Z digest=sha256:8e12e1243b418401eb9afd08c7e0236d5328803aab1962d33bb6b9c2a3335fdd

Observation c0c5c59e-0ee5-4ba8-94f0-7349e1a74c8a · outbound

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

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T13:34:16.540169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:34:16.540169Z digest=sha256:2a1499cd866617afba34b6b542e2fcffa6a46a1a3d8fc0c4b15f86977df2094e

Pith citing papers

Observation 5289f811-e60a-44fc-aef3-8421e4c95f59 · inbound

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cites this paper.

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 156

Resolution
metadata mismatch
arxiv_id, observed 2026-05-14T22:23:14.891136Z

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=2026-05-14T22:23:14.621091Z digest=sha256:de96f3a405cc194ae5dfd9c38602f7ee515f3adaf86e88ecf943555edaa56191

Observation 4d2494aa-d860-460c-af02-942321710354 · inbound

MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents cites this paper.

MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 42

Resolution
verified exact
arxiv_id, observed 2026-05-16T23:01:20.732591Z

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=2026-05-16T22:59:16.413568Z digest=sha256:85929073c33cd2b423de7d82aa6d2acd5f6d67901c8964f5a408d02ea794aefb

Observation 57332581-d9cf-46d9-8dae-1575766256bf · inbound

MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents cites this paper.

MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-03T16:38:36.511631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T16:38:36.511631Z digest=sha256:bc55a24820c98ec73838480105b5d751d5d89ee9294941c5803fba9cffa3dcd8

Observation 0eb2fcd5-bef3-4ff5-b6ed-4384ad800f34 · inbound

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents cites this paper.

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 34

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T10:31:00.883961Z

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=2026-05-10T15:28:07.981488Z digest=sha256:5a2595c36bbea70b39f9bb879c706bc6ee2bd826d82267c788aa39350da511c3

Observation c2fb5109-690a-4177-92e8-b942e493da8f · inbound

SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning cites this paper.

SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 20

Resolution
verified exact
arxiv_id, observed 2026-05-11T19:21:08.791996Z

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=2026-05-08T12:09:24.371878Z digest=sha256:6e86596a1a7c89a453c9e3ad5a50b09dc2032d8d7a51ec665e501d321ec5f29b

Observation 11271b9d-07e3-4faf-b2bd-ec8727698671 · 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 UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 116

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T04:35:56.386591Z

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:a539d7bc453aa14931d1b4f6700a7da6e73368b42ef07d15dbd20f93fc806a56

Observation 493f2919-3491-4dea-8426-4b60a7a5116e · inbound

Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment cites this paper.

Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 118

Resolution
verified exact
arxiv_id, observed 2026-05-15T01:58:28.784779Z

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=2026-05-15T01:58:19.295247Z digest=sha256:d73f6f6eb09d42eae9623182a2946168cccc6d62b06afc8a46133a8f57178afc

Observation 91a71e88-db5d-424b-aeeb-791f91cc0643 · inbound

Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment cites this paper.

Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 118

Resolution
verified exact
arxiv_id, observed 2026-05-19T16:47:40.442080Z

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=2026-05-19T16:45:16.963802Z digest=sha256:22578a99b067a97f13721f93092ebc69ce01a19e6582f628cedbb269462fe081

Observation 2ae10624-8280-4103-b73a-fe9c95337637 · inbound

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

A History-Aware Visually Grounded Critic for Computer Use Agents UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 28

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T05:17:40.284425Z

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=sha256:00a8f103a84c573893e0f127eaa27c93119c4b4978e0ca37e3d74b28a8c2e9ba

Observation 6c43ddee-4a08-41aa-813d-2e939f2a9333 · inbound

Software Engineering for and with GUI Agent cites this paper.

Software Engineering for and with GUI Agent UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

Reference 273

Resolution
unresolved
no resolver link, observed 2026-08-11T20:19:16.086843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T20:19:16.086843Z digest=sha256:cc17ba7682edd975d1f14a49313a016c39e181d9e87766e9f8512c6a73808176