Paper Citation Record · LEDGER

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

As of 22 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 2 inbound Pith citation observations for arXiv:2508.20018.

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

pith.paper-citation-record.v1
2508.20018 v1

Coverage vector

measured 75 of 75 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:18:57.759016Z

measured 77 of 77 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:18:11.054622Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T20:56:13.527455Z

Reference resolution

75 of 75 outbound references displayed

verified exact3
verified fuzzy6
unresolved66
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 19a9428a-3b77-4944-a35d-8b37187c5f34 · outbound

This paper cites Chain-of-Thought Reasoning In The Wild Is Not Always Faithful.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:50.382652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9247b188-b405-46f1-9e63-c098dcd87294 · outbound

This paper cites Qwen2.5-VL Technical Report.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:50.510010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b7b667c-f0b0-4f93-8021-8422d711e038 · outbound

This paper cites Distributed optimization and statistical learning via the alternating direction method of multipliers.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Distributed optimization and statistical learning via the alternating direction method of multipliers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:50.622301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f022b9-3a0f-4636-a5d4-c2f0a9355429 · outbound

This paper cites Multi-agent reinforcement learning: A review of challenges and applications.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Multi-agent reinforcement learning: A review of challenges and applications

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:50.743598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3fbfef5-8364-43bf-84be-fef9801b2dbc · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:50.874256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7693ce73-db26-4be6-956f-e200c9cea4bc · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control GUICourse: From General Vision Language Models to Versatile GUI Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:50.998350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b37cf8a-1c2e-437e-95f0-0a5b2c3764b7 · outbound

This paper cites Multi-agent deep reinforcement learning for large-scale traffic signal control.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Multi-agent deep reinforcement learning for large-scale traffic signal control

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:59.714977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cee11735-16f4-47b2-8c2f-cc3bc3750374 · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:51.219851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ab69ff-a89c-409e-af21-f5939873460b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Training Verifiers to Solve Math Word Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:51.304192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31f0b094-f876-40d6-88b3-88b02d3ba3a4 · outbound

This paper cites Process Reinforcement through Implicit Rewards.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Process Reinforcement through Implicit Rewards

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:51.436257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc4c11f-ff7c-463c-8aba-3745abd36ad5 · outbound

This paper cites Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:51.513389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c28e3fa-83d7-488c-847c-7abee908cccf · outbound

This paper cites Improving factuality and reasoning in language models through multiagent debate.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Improving factuality and reasoning in language models through multiagent debate

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:51.621480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a78a3a-f459-42be-9329-c28463a4b888 · outbound

This paper cites Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:51.734773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd2a098-f0f9-4964-882c-fd237304bff4 · outbound

This paper cites On alternating direction methods of multipliers: a historical perspective.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control On alternating direction methods of multipliers: a historical perspective

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:59.677196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0d5f1473-ec08-49cf-adb0-92ed47a6983b · outbound

This paper cites Towards Efficient Multi-Agent Learning Systems.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Towards Efficient Multi-Agent Learning Systems

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:18:59.149753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6a21393a-2d07-49a2-841b-36ec9af8bfe8 · outbound

This paper cites Seed1.5-VL Technical Report.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Seed1.5-VL Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.028713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb744fa-3099-443c-8f5c-25843fb7e772 · outbound

This paper cites LLM Multi-Agent Systems: Challenges and Open Problems.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control LLM Multi-Agent Systems: Challenges and Open Problems

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.148823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c21b1c-42f9-43f4-9768-03b570521f72 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Measuring Mathematical Problem Solving With the MATH Dataset

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.263559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e0bcf3f-125c-4b0a-83a4-b367c3b90271 · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.384772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd5fd225-1cce-4510-83b4-7298b75cac67 · outbound

This paper cites OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.500880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 479c9983-0611-44a2-a6f6-92044d09bca0 · outbound

This paper cites Qwen2.5-Coder Technical Report.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Qwen2.5-Coder Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.630612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53723fdb-ad20-4a58-8efc-0330967c96f2 · outbound

This paper cites Omniact: A dataset and benchmark for enabling multimodal generalist autonomous agents for desktop and web.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Omniact: A dataset and benchmark for enabling multimodal generalist autonomous agents for desktop and web

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:59.653591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 516ac072-e338-4278-8f3a-b64ce774873d · outbound

This paper cites Os-harm: A benchmark for measuring safety of computer use agents.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Os-harm: A benchmark for measuring safety of computer use agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.862777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebb81904-c3bd-4d6b-a063-2e0271315e49 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Gonzalez, Hao Zhang, and Ion Stoica

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:52.977243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5005a91c-eea3-4a3f-8c6b-4264ded03b52 · outbound

This paper cites ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.098539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dd64cb2-b43d-4f66-ab36-7672dd6ce78c · outbound

This paper cites Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.252747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8bc6389-2215-4eb6-b20b-a0c28e13307d · outbound

This paper cites On the Effects of Data Scale on UI Control Agents.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control On the Effects of Data Scale on UI Control Agents

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.370344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7284a6bd-a9f8-495d-a1aa-f45307bd4211 · outbound

This paper cites MARFT: Multi-Agent Reinforcement Fine-Tuning.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control MARFT: Multi-Agent Reinforcement Fine-Tuning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.497423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b9a3d2f-7874-4a61-8926-71a1fd82fa76 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.536887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 458cafae-0407-4869-9f4c-0e3ea612a27f · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.611757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c2810cd-48c7-49a7-8fa4-e2f458c9bf5a · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.726458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a582d7b-166c-462e-a4f8-e4788bf0d221 · outbound

This paper cites GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.855437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49d3dfd9-8be8-4b2a-928c-4195f544d630 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:53.972497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09649300-7f31-4425-9b3b-92956ccfcfbc · outbound

This paper cites Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:54.078626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdbf12c8-a705-442d-aefb-097151b4c606 · outbound

This paper cites ScreenAgent: A Vision Language Model-driven Computer Control Agent.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control ScreenAgent: A Vision Language Model-driven Computer Control Agent

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:54.236190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d78ccc9-e24d-4360-8109-b5a779693a66 · outbound

This paper cites Introducing gpt-5.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Introducing gpt-5

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:59.614982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3b7fe2e0-b28c-4a28-af38-7d38bba51389 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:54.490511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de128de1-a07d-49ec-a34e-c52f80ad201d · outbound

This paper cites Monotonic value function factorisation for deep multi-agent reinforcement learning.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Monotonic value function factorisation for deep multi-agent reinforcement learning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:54.649045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b1898c5-e4b7-4cb8-a89d-fab0c23d349a · outbound

This paper cites SAM 2: Segment Anything in Images and Videos.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control SAM 2: Segment Anything in Images and Videos

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:54.784911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8eb95c4-8a04-4a12-9b7e-00b83ed2644f · outbound

This paper cites Android in the Wild: A Large-Scale Dataset for Android Device Control.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Android in the Wild: A Large-Scale Dataset for Android Device Control

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:54.955390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee5652ef-c26f-4dd3-aada-6a145d69455b · outbound

This paper cites Trust region policy optimization.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Trust region policy optimization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:55.056102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05916953-5ccd-4cb2-90e9-7a4c871e725b · outbound

This paper cites Proximal Policy Optimization Algorithms.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Proximal Policy Optimization Algorithms

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:55.169460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2203b9-d430-43a6-96c6-5973b923525a · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:55.330893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cafeca55-bc45-4a98-9a89-3e4a2671c7c3 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Hybridflow: A flexible and efficient rlhf framework

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:55.493051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a1a5993-fd84-49b9-85bc-de438734ccf1 · outbound

This paper cites Towards trustworthy gui agents: A survey.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Towards trustworthy gui agents: A survey

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:55.630193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e37ba6-4650-44be-9ec0-6ace697b82f9 · outbound

This paper cites Teaching Models to Balance Resisting and Accepting Persuasion.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Teaching Models to Balance Resisting and Accepting Persuasion

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:55.797459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42ad7824-693b-46b6-be49-870abb151ffb · outbound

This paper cites Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:55.902002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06b385d4-bb0a-4e4e-8317-be9f29a75b0d · outbound

This paper cites Value-Decomposition Networks For Cooperative Multi-Agent Learning.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Value-Decomposition Networks For Cooperative Multi-Agent Learning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:56.030027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efee8467-2e75-4412-b4ee-714b52fea9a2 · outbound

This paper cites GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:56.155953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ea87f0f-c321-4b53-88f4-05c8e77552d2 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:56.487424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15dfc07d-049f-45d0-b2ef-0db6b380bb91 · outbound

This paper cites Language models don't always say what they think: Unfaithful explanations in chain-of-thought prompting.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Language models don't always say what they think: Unfaithful explanations in chain-of-thought prompting

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:56.755000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36e0ce03-7710-4111-bb7d-cc717cf9c8ed · outbound

This paper cites GUI Agents with Foundation Models: A Comprehensive Survey.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control GUI Agents with Foundation Models: A Comprehensive Survey

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:56.900795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5853eb5-71da-4db5-a308-a125ecdc7a41 · outbound

This paper cites Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.030594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4aa2014-ce7f-4a6d-bfa6-8d1e0746810c · outbound

This paper cites Order Matters: Agent-by-agent Policy Optimization.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Order Matters: Agent-by-agent Policy Optimization

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:18:58.169804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4ac9fbff-9eb4-47ba-b500-9f9db7afe815 · outbound

This paper cites Mp-gui: Modality perception with mllms for gui understanding.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Mp-gui: Modality perception with mllms for gui understanding

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:59.533792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9a0bd143-9fe1-4573-be92-c8a2cd182172 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Chain-of-thought prompting elicits reasoning in large language models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.352490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c95e31b8-acbe-416a-93d9-b2944dca21e5 · outbound

This paper cites CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.423607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbbc11b9-4f2a-471b-9fcc-94d29a09fc57 · outbound

This paper cites Autogen: Enabling next-gen llm applications via multi-agent conversations.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Autogen: Enabling next-gen llm applications via multi-agent conversations

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.545356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7648e41d-0bf0-4f75-911c-fcebbbcfce67 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.651708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12716f24-d199-44e6-a838-6115cd11bfe8 · outbound

This paper cites Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.675232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8517c31a-4e46-4c87-a23f-9a9cacc65512 · outbound

This paper cites TradingAgents: Multi-Agents LLM Financial Trading Framework.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control TradingAgents: Multi-Agents LLM Financial Trading Framework

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.680409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a10d33a-8219-4629-be6d-f6b3f46e4223 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.686718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62017697-9004-444f-bc61-ed919caba547 · outbound

This paper cites A Survey of ADMM Variants for Distributed Optimization: Problems, Algorithms and Features.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control A Survey of ADMM Variants for Distributed Optimization: Problems, Algorithms and Features

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.691983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acbf7106-55c1-414b-9fcf-700eac3af2cc · outbound

This paper cites Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.697193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d4c849e-b94b-4919-854d-6ae0ccbc72bf · outbound

This paper cites Android in the Zoo: Chain-of-Action-Thought for GUI Agents.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Android in the Zoo: Chain-of-Action-Thought for GUI Agents

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.701929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54090172-8602-4cd3-a23d-2e31ad3adf6e · outbound

This paper cites Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.707774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68065708-a7ee-4821-a03d-6e3de2cb1aee · outbound

This paper cites LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.713495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1f48cc3-e73f-4732-98c0-d28292401d05 · outbound

This paper cites SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.718882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae57306c-22d6-4f8f-adc4-9a549141dbf7 · outbound

This paper cites An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making

Reference 69

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:18:57.856062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 255449bd-01f8-40f9-952c-d365d48d31fc · outbound

This paper cites Heterogeneous-agent reinforcement learning.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Heterogeneous-agent reinforcement learning

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:59.481072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 94bccebf-59c1-42b4-8859-a20ac12ff831 · outbound

This paper cites GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.734021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f85316-a1b2-4b03-8e32-8a89c58b8ed1 · outbound

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

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.739096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15fab545-d472-4144-b1a3-d03e31c4904f · outbound

This paper cites @esa (Ref.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control @esa (Ref

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.745032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 965654c6-fcef-47ac-a38e-df6f1c5d873b · outbound

This paper cites an unresolved cited work.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Unresolved cited work

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.753369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4935e77-8b93-42f9-9a55-92011d974d5f · outbound

This paper cites an unresolved cited work.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Unresolved cited work

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:57.759016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9d05a0cc-0145-4168-b782-a48fe1b9e486 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:56:13.528809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d7be8218-0e2a-4828-bc27-b9e00949bb21 · inbound

When the Judge Should Not Decide: Evidence-Locked, Non-Compensatory Selection Bounds LLM-Judge Failure in Reasoning Pipelines cites this paper.

When the Judge Should Not Decide: Evidence-Locked, Non-Compensatory Selection Bounds LLM-Judge Failure in Reasoning Pipelines SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T04:18:11.054622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.