Paper Citation Record · LEDGER

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

As of 8 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 16 inbound Pith citation observations for arXiv:2505.16282.

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

pith.paper-citation-record.v1
2505.16282 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:07:10.796768Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:25:14.276099Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T20:00:08.408321Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy5
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a97a4621-6c2e-4838-8b44-aac68c14df56 · outbound

This paper cites Qwen2.5-VL Technical Report.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:08.732949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5544cf9-7703-4840-aa66-c648472154de · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:08.818285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06a674f1-8a7e-48ab-8c65-6f05654887e2 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay KTO: Model Alignment as Prospect Theoretic Optimization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:08.943210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a204acfe-dfc4-4120-a7ae-98cec497d88e · outbound

This paper cites Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.054423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a71639-ea78-4543-8235-922a76b611cc · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.148499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2923ec7-65ca-4e66-a110-9ab98fa6804c · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Cogagent: A visual language model for gui agents

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:07:11.440915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 08626187-7624-473a-848e-7420015aef08 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.358618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48d13b54-9277-4d20-9f3b-7d8563c4eae4 · outbound

This paper cites OpenAI o1 System Card.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay OpenAI o1 System Card

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.452790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5481a0-74d7-401d-881c-9dac23cee2e4 · outbound

This paper cites OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.526745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0a72d0c-1f2b-439e-b76a-0815a1f77501 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Efficient memory management for large language model serving with pagedattention

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:07:11.374189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 723a7e63-be07-4902-9360-6ab11888e498 · outbound

This paper cites Code-r1: Reproducing r1 for code with reliable rewards.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Code-r1: Reproducing r1 for code with reliable rewards

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.737013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ea43a1d-8027-47f5-b596-6acbc00c0eb8 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.853262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7d8539-4150-48cb-832c-6b4548dd2e82 · outbound

This paper cites Decoupled Weight Decay Regularization.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Decoupled Weight Decay Regularization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:09.981894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a897a41-6265-4c2c-abd7-a4289024e73f · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay ScreenAgent: A Vision Language Model-driven Computer Control Agent

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.028219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53b21184-ee19-4e15-a7de-b8d3d4fa34d7 · outbound

This paper cites ToolRL: Reward is All Tool Learning Needs.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay ToolRL: Reward is All Tool Learning Needs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.067180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202e5032-e30c-4814-905a-6ed48af0b141 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.120332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15b11a46-da31-4f47-aea5-c4c68fc8cadd · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Direct preference optimization: Your language model is secretly a reward model

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:07:11.288367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1f8adde8-ef64-4dfe-a2b9-59b519a037ef · outbound

This paper cites Proximal Policy Optimization Algorithms.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Proximal Policy Optimization Algorithms

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.211575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d28fa66-0dad-4959-9ec7-efc2a223b9c2 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.279353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 440ba8ab-3650-4f73-bf52-0b10af21267c · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay HybridFlow: A Flexible and Efficient RLHF Framework

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.332778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ababca5-5736-47a2-924b-fd00f9d5b887 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.363216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eda3ee73-fe85-4711-a4cc-bec481c35515 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Chain-of-thought prompting elicits reasoning in large language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:07:11.194077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8f180272-3fd7-41f7-af45-ed5731c23050 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.444576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f4df80-56d4-438d-8f34-5af8fc91a67a · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.491309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d6f9ea-76b2-4537-a06c-9ecfa4747bd3 · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:07:11.128405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ca674936-63b4-4926-aa11-f4c6420fc5b6 · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.588099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a363f308-e927-4e0c-9fbf-e202d39c717e · outbound

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

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay Aria-UI: Visual Grounding for GUI Instructions

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.649086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9423a99-3bc6-4f52-a8cb-ee85a07db547 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.758735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b169f929-fb11-4c83-8be7-a284473d8032 · outbound

This paper cites SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks.

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:07:10.796768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c7df2476-8c0a-48d9-8a9f-2cf60b09acd7 · inbound

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment cites this paper.

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:25:14.276099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efa7606d-90a1-4c89-a24d-f755e76324f5 · inbound

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning cites this paper.

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-13T10:13:59.047730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0acd32bd-456b-4de0-87eb-b50696880523 · inbound

Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning cites this paper.

Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T12:52:27.271355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61c88db6-3fd5-4294-852b-ee3cc6395ca1 · inbound

AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning cites this paper.

AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T16:30:39.322149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a6fa83-59c1-42f8-bd82-ecc76dcd26e5 · inbound

Agentic Reasoning for Large Language Models cites this paper.

Agentic Reasoning for Large Language Models ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-17T15:14:25.866371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a00a8d54-94c6-4eff-8a4b-afedab8048e3 · inbound

Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization cites this paper.

Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-15T20:36:35.212903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 32ddfcb8-f0f4-4f19-ad06-b0543b4f3018 · inbound

Faithful Mobile GUI Agents with Guided Advantage Estimator cites this paper.

Faithful Mobile GUI Agents with Guided Advantage Estimator ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:41:24.147115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3ab69e72-872e-4417-b40f-66d6b72ad9eb · inbound

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length cites this paper.

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:40:40.641959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 61a0ea97-88b7-4880-83e2-222fca09fa1a · inbound

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization cites this paper.

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:01:17.873771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e43a52a5-801e-44c0-a4e7-1f00e7d6cdf0 · inbound

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization cites this paper.

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:17:07.683646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 494b1bdb-c798-4aa8-b384-8e948dd3bd4f · inbound

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents cites this paper.

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-13T03:52:12.365420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad7335ec-cd17-4d1b-85cc-f1e71fcfc475 · inbound

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning cites this paper.

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-01T21:16:13.369302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 44daa594-25cc-420c-a599-f689908c2cdb · inbound

StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents cites this paper.

StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:47:09.594291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 46e7f937-ef14-4065-9ae5-ae9c9c4aa368 · inbound

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning cites this paper.

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 125

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:09:40.731617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3450fa5e-24d1-467e-99a6-dbf7f0c44049 · inbound

Learning with a Single Rollout via Monte Carlo Pass@k Critic cites this paper.

Learning with a Single Rollout via Monte Carlo Pass@k Critic ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T20:00:08.409789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 490492e7-74a4-411e-afa8-b66bcd8c2a8d · inbound

DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents cites this paper.

DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:53:26.532661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.