Pith. sign in

Paper Citation Record · LEDGER

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

As of 22 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 10 inbound Pith citation observations for arXiv:2506.00618.

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

pith.paper-citation-record.v1
2506.00618 v3

Coverage vector

measured 69 of 69 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:06:29.178864Z

measured 79 of 79 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 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:46:06.025109Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T10:15:44.749818Z

Reference resolution

69 of 69 outbound references displayed

  • verified exact0
  • verified fuzzy15
  • unresolved54
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 284988e6-016b-48e4-b6ee-e89aa93bbbdf · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Agent S: An Open Agentic Framework that Uses Computers Like a Human

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:22.590276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:22.590276Z digest=sha256:793e14e4e81cd14190ad9158c39f5e9179a66364bf15a76069e9d714700de234

Observation 5e0d7b01-54a6-44a2-9c25-6f91021d9e8c · outbound

This paper cites Attacking multimodal os agents with malicious image patches.arXiv preprint arXiv:2503.10809, 2025.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Attacking multimodal os agents with malicious image patches.arXiv preprint arXiv:2503.10809, 2025

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:22.686046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:22.686046Z digest=sha256:ac64d19135a12dfc865dc9549e636b4b78b04118ecd303a6a0cca45c90200ed2

Observation 457ecadb-2fa0-4c52-b68d-af978cbd43bc · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:22.753457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:22.753457Z digest=sha256:caec14ed0fbb0e7bb48cd63ac2eaa94032e7c5bdc1214a53cb84a544f9424010

Observation 8f9d311f-9945-4c27-b3ec-2821158f37f3 · outbound

This paper cites Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku, October.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku, October

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:34.359550Z

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.

source=pdf_text observed=2026-08-07T12:06:22.867309Z digest=sha256:cc2f12a032419a6e488bdb3f8a0bb7d565e848decf4073fdc56e7add1312230c

Observation 64218e8f-8491-4f08-986b-40d6d266ad9e · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.https://www- cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf, 2024.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents The claude 3 model family: Opus, sonnet, haiku.https://www- cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf, 2024

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:34.036970Z

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.

source=pdf_text observed=2026-08-07T12:06:23.019663Z digest=sha256:9d310cbaad5f8c2e806211cc0ea00fcb67fe30ab87519c1ce27a1bf454389543

Observation c2bb2ada-3d80-4f13-bf05-f14fc7c0363f · outbound

This paper cites Claude 3.7 sonnet system card, October 2025.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Claude 3.7 sonnet system card, October 2025

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:33.880157Z

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.

source=pdf_text observed=2026-08-07T12:06:23.095720Z digest=sha256:20d591dd45ea246cd70616ffa3537e00a17709d2bc5a5be7433fc5b63ff56fff

Observation 4ee72da9-71eb-4ad0-b1cf-d867dd7d1307 · outbound

This paper cites Developing a computer use model, October 2025.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Developing a computer use model, October 2025

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:33.712367Z

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.

source=pdf_text observed=2026-08-07T12:06:23.186031Z digest=sha256:a2f57058457a59cbe0d3c2840435dd1a2594c51391b8aca979c94fd9d2b2eaa7

Observation c77596af-e757-439b-aa3f-30285f37420d · outbound

This paper cites Qwen Technical Report.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Qwen Technical Report

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.264319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.264319Z digest=sha256:7ebb967b5341e667f0ec81fa8ba514c3e9da7b6eb39f3b331f83710dd93f7705

Observation a677f3b9-b95b-4396-a6a1-800e2e8b4acb · outbound

This paper cites Qwen2.5-VL Technical Report.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Qwen2.5-VL Technical Report

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.352657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.352657Z digest=sha256:f21f05f5c9c336d8a1db694dd64e8ca7e7e241541d61b2e8761727cebbe3dae8

Observation 34eb453f-4baa-4326-8391-5f36d87d19e0 · outbound

This paper cites Octopus v2: On-device language model for super agent.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Octopus v2: On-device language model for super agent

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.410305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.410305Z digest=sha256:4b8326813d77306b1e2ecf1d47d3136148e218fe79f8eb529e64207f4281dc83

Observation c47314d5-2658-400b-99eb-4c3d9768afa4 · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.503732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.503732Z digest=sha256:23f24dba4247388b808b2133e9025d5e438e2d46dac09ad794876e935edd91ac

Observation bbdb7fac-8879-4cc8-bc8b-dadea32a3828 · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.592039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.592039Z digest=sha256:ba0b20141223b8332b3fd76c85f044ba2d17bc112305359921417d56b1983b4d

Observation 029cf64f-9676-4e24-850d-801b0376976c · outbound

This paper cites WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.663176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.663176Z digest=sha256:de394ce1d0edda0d102ca9576c65cfa574c00f6e199db7aec26b59eef2b32ab8

Observation f0688495-ce81-4327-b012-24fd294e647b · outbound

This paper cites The Llama 3 Herd of Models.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents The Llama 3 Herd of Models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.757644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.757644Z digest=sha256:92b4ff9caae991f11b1bdd0249783a661a35cd98c3d5f9717055d196fa14d4f3

Observation 9b662792-2707-4c6c-b155-9bd26d621df6 · outbound

This paper cites WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.848988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.848988Z digest=sha256:0d199561e0f3e81a7f1fac372b07803f7262ca30decf49eb7367419952a55e43

Observation e965dfe2-4db4-4e8e-bb1c-53e32202773a · outbound

This paper cites GPT-4o System Card.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents GPT-4o System Card

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:23.968062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:23.968062Z digest=sha256:17ec02e5514d15bba0d381e6ffc912c64175f6eaaa71195e3901c87b25b5623c

Observation b2618616-389b-4c92-bcca-a80cbc730f06 · outbound

This paper cites OpenAI o1 System Card.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents OpenAI o1 System Card

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.068502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.068502Z digest=sha256:56560d6541fc8dec454edf5e6967ec839d5294684c9a065cc797415dc8598d9a

Observation a403411d-81b7-42cd-8ddd-153941fee54e · outbound

This paper cites SWE-bench: Can language models resolve real-world Github issues? InThe Twelfth International Conference on Learning Representations, 2024.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents SWE-bench: Can language models resolve real-world Github issues? InThe Twelfth International Conference on Learning Representations, 2024

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:33.499982Z

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.

source=pdf_text observed=2026-08-07T12:06:24.139358Z digest=sha256:8f9ffc3333b6112a9c0e51101fab111340d07c0b858a31372b8ff5274aaa5eac

Observation c8a04038-099c-44f2-9b0c-eaf15b9ca3c2 · outbound

This paper cites VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.215598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.215598Z digest=sha256:0cff8189467d2759cb8e7c9d2c221977cf91fb003ee02c57f6b9dc410dc734ad

Observation ebc3a157-94e5-4f86-b624-6796770c4735 · outbound

This paper cites Autowebglm: A large language model- based web navigating agent.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Autowebglm: A large language model- based web navigating agent

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.325954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.325954Z digest=sha256:31008196c2bb9a6308e560b486722565d2e4c84c6fe5b341518275bc78d2255e

Observation 588e37ac-892c-4bbe-9e0d-a54bec4c8327 · outbound

This paper cites Mobilesafe- tybench: Evaluating safety of autonomous agents in mobile device control.arXiv preprint arXiv:2410.17520, 2024.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Mobilesafe- tybench: Evaluating safety of autonomous agents in mobile device control.arXiv preprint arXiv:2410.17520, 2024

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.447633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.447633Z digest=sha256:3dc63af27d73f68023354b10508763ff2facf9e268397569778e7722ac7917cc

Observation 94e1e1ff-014d-44b5-8874-cf613ebe8c4b · outbound

This paper cites ST- WebAgentBench: A benchmark for evaluating safety and trustworthiness in web agents, October.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents ST- WebAgentBench: A benchmark for evaluating safety and trustworthiness in web agents, October

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:33.271607Z

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.

source=pdf_text observed=2026-08-07T12:06:24.550937Z digest=sha256:0f756021dc40f445823fbaf546fbc28308b72fa3094f94a9a7b72debbf82b135

Observation 11b9720f-17e5-4452-b75f-8a4a47c42ef0 · outbound

This paper cites EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.688608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.688608Z digest=sha256:08756a06c7c156ea84fc141b1d2fb2138ceda5017e4bf17a4a4b10fcab30c4c6

Observation aaf56cf0-5b9d-427e-95cf-2d46ceaf3b80 · outbound

This paper cites ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.612239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.612239Z digest=sha256:26d760bcfad840d328c1ad1d9931760c43dc8bed3cfccba2b9dc1b2a990e1ac2

Observation e3a15162-a7d8-4038-b57f-9acdb5af51e4 · outbound

This paper cites Large language model-based agents for software engineering: A survey, September.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Large language model-based agents for software engineering: A survey, September

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:33.104616Z

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.

source=pdf_text observed=2026-08-07T12:06:24.847496Z digest=sha256:ce11a87cfc095378a28f525657e7e7d2b1c43d4245dc2bd90ba69d83cb32de47

Observation 038741e4-74ad-4c5c-9a4a-56f7f7ac5b94 · outbound

This paper cites ShowUI: One Vision-Language-Action Model for GUI Visual Agent.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.763166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.763166Z digest=sha256:0f5a92ed6b79fd6a462cac0505c67ece2216dbdc6595fb1153ceede6bf1b0193

Observation 03241d5c-d09c-4935-827f-a8682c9e436b · outbound

This paper cites CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:25.162426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:25.162426Z digest=sha256:7920aa348c172b208b599858739adf0080c3412f2cda87535a632d4fce9f6e6b

Observation fda4c8a5-c71b-4d21-b977-b7e32457ba21 · outbound

This paper cites Large Language Model-Based Agents for Software Engineering: A Survey.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Large Language Model-Based Agents for Software Engineering: A Survey

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.945129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.945129Z digest=sha256:fd14991e2067be337c1f39086fac8e6e89ea1267bccca651937bb0af4f3797ea

Observation c9e9e7d1-8aaa-4348-ae3b-32b7af5095b0 · outbound

This paper cites Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:24.997627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:24.997627Z digest=sha256:866eb0feb59996759052770c222e9a93346368b796c5f6a13e80e3addb446225

Observation 5de20775-65e0-4c4d-9fff-94a03f9b5bcb · outbound

This paper cites nightly/daily builds.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents nightly/daily builds

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:32.712424Z

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.

source=pdf_text observed=2026-08-07T12:06:25.440932Z digest=sha256:b9da90b0f81b0d7c3b4e6939455a928d6d610497b00b3769ac83dc8aba4821b2

Observation f2827640-58b0-4763-9238-cbd5d2e29986 · outbound

This paper cites Manus ai: a universal ai assistant that can transform your ideas into actions, 2025.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Manus ai: a universal ai assistant that can transform your ideas into actions, 2025

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:32.863721Z

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.

source=pdf_text observed=2026-08-07T12:06:25.230337Z digest=sha256:fff5b57430adb13807d6146186a25bb41a94efae8e246e7daa99bc59d0ad2a48

Observation 9b0e310f-50f2-4e14-8168-d746c1a53d67 · outbound

This paper cites FLIN: A Flexible Natural Language Interface for Web Navigation.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents FLIN: A Flexible Natural Language Interface for Web Navigation

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:25.336004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:25.336004Z digest=sha256:4b759fdfbc6c18e6d73e36730e4abd230ea4034d6803fc29d6e5490bae27ad83

Observation 4462c3d3-e7f7-418c-ad67-8f55354b8925 · outbound

This paper cites Roscript: a visual script driven truly non-intrusive robotic testing system for touch screen applications.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Roscript: a visual script driven truly non-intrusive robotic testing system for touch screen applications

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:32.412319Z

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.

source=pdf_text observed=2026-08-07T12:06:25.774003Z digest=sha256:79538d1a76189e15e8b178fae4deaf2ddfa9acfb4d9bb6a3bdca06e0ad8c9f20

Observation 8f812064-c74d-4b95-b877-afeee57352c2 · outbound

This paper cites Computer-Using Agent: Introducing a universal interface for AI to interact with the digital world, 2025.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Computer-Using Agent: Introducing a universal interface for AI to interact with the digital world, 2025

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:32.531191Z

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.

source=pdf_text observed=2026-08-07T12:06:25.562633Z digest=sha256:b09a0e7d21b2c877c3c877d3912f81680ba270d2ee89493d3cdffb6acebcdd62

Observation 4f5875be-c1ad-48d0-a7ef-be1eb45a8f7f · outbound

This paper cites GPT-4 Technical Report.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents GPT-4 Technical Report

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:25.667552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:25.667552Z digest=sha256:9b0e52215cda2673b1dcb85d33958285fdaac89041b2e59f4ff258428fbf352e

Observation 2f970317-af43-4050-a55e-7c6f225a1dfd · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.116515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.116515Z digest=sha256:aef6ddefcc8f9cdcdc7466f079cdbeff77a5de13a2152b401601b31ed8c310b2

Observation 9930c096-1ea4-446d-808e-0e618fead237 · outbound

This paper cites An- droidinthewild: A large-scale dataset for android device control.Advances in Neural Information Processing Systems, 36:59708–59728, 2023.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents An- droidinthewild: A large-scale dataset for android device control.Advances in Neural Information Processing Systems, 36:59708–59728, 2023

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:25.915682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:25.915682Z digest=sha256:7ceb83747fde8f4bce134d5e62486c61aa08473d92bb8148049fdd3af6b28a54

Observation 4d82527d-7030-4595-9126-52f889bb9ca1 · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.003533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.003533Z digest=sha256:c5cfb3d159801f122d987d8897c3b61505e82f339a6c1f5b25aae493e4c986a2

Observation 242886f9-7c24-4c9d-a98c-8ae3463f74de · outbound

This paper cites META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.528417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.528417Z digest=sha256:16bc43b9f3d38045c5794fa3dda4a7c65b6ebe58b775958824f131db492eb65f

Observation 0134cf90-712e-4a33-9f88-4b7e5ee96823 · outbound

This paper cites Identifying the Risks of LM Agents with an LM-Emulated Sandbox.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Identifying the Risks of LM Agents with an LM-Emulated Sandbox

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.269044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.269044Z digest=sha256:b33c11a25608d0764e179044245194d32984a7e53600f6a9db28e6036f627740

Observation 6c36f7e1-9ca0-461e-8d3b-b17cfc4f6a6b · outbound

This paper cites World of bits: An open-domain platform for web-based agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents World of bits: An open-domain platform for web-based agents

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.372738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.372738Z digest=sha256:4fc50bddcb0e3a5fa5d1b1e4647684eec9751087233a99cd6c61aa077a401bec

Observation a5c77f8b-7556-4ec2-a7ce-abfab940e084 · outbound

This paper cites SafeArena: Evaluating the Safety of Autonomous Web Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents SafeArena: Evaluating the Safety of Autonomous Web Agents

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.862588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.862588Z digest=sha256:c11945854aa3c317d0e4406289587e906dfc7b51bca514452ce3fdcb1ecefe7b

Observation 789e627a-8e40-4533-924d-3036e3323756 · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Gemini: A Family of Highly Capable Multimodal Models

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.652241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.652241Z digest=sha256:b40da37649e37a99b3ec5485725185029653eaaff68d366ce8e2b1004814f4d4

Observation 072e9111-6972-4ef9-9353-cc8650932af2 · outbound

This paper cites Anthropic, 2024.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Anthropic, 2024

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.748863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.748863Z digest=sha256:666e2d4342950f7c2d6253fd124369127d228529b84377390f400b469ea7b337

Observation 85ccfadf-ebd4-4392-b29a-a9eac925d76d · outbound

This paper cites WIPI: A New Web Threat for LLM-Driven Web Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents WIPI: A New Web Threat for LLM-Driven Web Agents

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.120706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.120706Z digest=sha256:64c5ba4578e085022fa7ed8310d59b5346f7ddab1af95d23383cdf5a59e881bf

Observation 46b14f9f-f75d-437e-a271-de3dce4bc275 · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:26.962871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:26.962871Z digest=sha256:1ced14a5b567e3747d9c4a8aea17b3c979b6a7c963813c3eef21013a8fbf00c7

Observation fa21ad3d-c8e7-40f9-ab5c-b12894695053 · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.049458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.049458Z digest=sha256:ead9ef9250f5b82b1c730aed1abb1b2d326e86ad440a0e2133745652e48df336

Observation 2dbfab8a-e111-4091-8d2a-76d09e757829 · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.404090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.404090Z digest=sha256:07b5d2046c8969dc3ff8be4179e9c155cf879ba73093485c6d215461f099e9e6

Observation 2a6ef5ce-6c1b-43c0-b5db-30d3ff956a2e · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.217615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.217615Z digest=sha256:24dfd94da8037cd39d9858efe2e1138b46bd27f1b8cc886b7d566e8c62f831d4

Observation 811cc1c0-f73f-414a-a0ba-562fbc81413b · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.Advances in Neural Information Processing Systems, 37:52040–52094, 2024.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.Advances in Neural Information Processing Systems, 37:52040–52094, 2024

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.317673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.317673Z digest=sha256:be74eb5c79ae545a43d23734cd7441543c94eda79571fd2033316cb2c9ce7403

Observation 09020643-a387-4b8d-8cec-fc86ef88ebf8 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.641818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.641818Z digest=sha256:cf24d9f1fef94343d21687fc0fe7a326aaa4d88c97ad96eafbe543a376d9e350

Observation 116a9072-7d6e-4ba1-a163-1e0e254335f8 · outbound

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

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents React: Synergizing reasoning and acting in language models

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.525969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.525969Z digest=sha256:5c41ae875550ead8a68241d3d2ad8f9d24cf108d2755548e8601e79bab42e127

Observation 24801c2b-85b4-4807-9e59-e076dfa33945 · outbound

This paper cites ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.595232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.595232Z digest=sha256:4e9f3ecb4ec8bba1ef5545cfc11c5264fcd6488cf7129b03d48db212af8b1860

Observation f232dac0-63ab-4f5c-ad68-c9c6f86410e4 · outbound

This paper cites Attacking Vision-Language Computer Agents via Pop-ups.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Attacking Vision-Language Computer Agents via Pop-ups

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.951327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.951327Z digest=sha256:242afd5e670cf623bebc1bfd13abf56a302d5a78d219abc8372e4c58cf1a74af

Observation a8643598-2ce1-41fc-9c5f-e3d373f67833 · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.758031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.758031Z digest=sha256:98c8ed7a7f2218c4f89b16302350c9e97cba00ea501efea8c7701f84cc53ece4

Observation 1cc439e2-24d8-47b0-a979-7578ef8845a7 · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:27.869822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:27.869822Z digest=sha256:e13734b5a762e41c98ae06a1877d580410fe19fa1cea3f15b138322a50ff2afb

Observation e4c187fe-c83d-4cdb-b220-1e539871d037 · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:28.195185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:28.195185Z digest=sha256:253d49da493805a05cd570105521e3a6f30de6cdd7d78769b606a240b8084291

Observation 762d0332-b4e4-44bf-b5ae-5e298ca3022f · outbound

This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Agent-SafetyBench: Evaluating the Safety of LLM Agents

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-07T12:06:28.033298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:06:28.033298Z digest=sha256:ebce92dc7a3e71208879afcdca9ec244e13dc3dd300adac14490f462468e1d99

Observation 24bd7cb8-7db8-4e7c-85a6-f20005d4f264 · outbound

This paper cites You only look at screens: Multimodal chain-of-action agents.arXiv e-prints, pages arXiv–2309, 2023.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents You only look at screens: Multimodal chain-of-action agents.arXiv e-prints, pages arXiv–2309, 2023

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:32.208175Z

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.

source=pdf_text observed=2026-08-07T12:06:28.117482Z digest=sha256:565d9ebdeff805823099945f3c68045ae433435123dd583136923c6e1363d9a6

Observation 7b5daac3-7cb3-4d01-ade7-d7bf3c1bf4f0 · outbound

This paper cites Phishing Web.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Phishing Web

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:32.057095Z

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.

source=pdf_text observed=2026-08-07T12:06:28.321182Z digest=sha256:478f599592e3ee2560ab06772e229b331c483e5da18156d77f5c630b1e22bf66

Observation a38d2aa6-72d7-46c9-9ab4-42545c883ca5 · outbound

This paper cites an unresolved cited work.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Unresolved cited work

Reference 63

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:06:31.883064Z

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.

source=pdf_text observed=2026-08-07T12:06:28.438579Z digest=sha256:8768d78259aef42041120fb71a57c6776151cd0b850657b29e7cd20ee014feaf

Observation da92d423-d219-4f17-85db-dbaf18f5f290 · outbound

This paper cites an unresolved cited work.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Unresolved cited work

Reference 64

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:06:31.704383Z

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.

source=pdf_text observed=2026-08-07T12:06:28.540014Z digest=sha256:e00c6ce452115703c027ddec589e8d455477a2ee6f561b11e4200cad45edadd4

Observation f2776078-2b53-4142-90f3-22fb17e5b37b · outbound

This paper cites an unresolved cited work.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Unresolved cited work

Reference 65

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:06:31.471539Z

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.

source=pdf_text observed=2026-08-07T12:06:28.634621Z digest=sha256:14eb3f2cdd20afa6f14d4cfc24cdecd5fc5aa212cbb6d4454a03a63e9b1899f1

Observation 3e7c40a9-c097-47b9-85db-4230d421cb47 · outbound

This paper cites log USDT transaction.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents log USDT transaction

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:31.258956Z

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.

source=pdf_text observed=2026-08-07T12:06:28.741236Z digest=sha256:226b5a5e41811d14ef6fe05b2327dbe5a279d94fe9f317baecee0c4cd5390e44

Observation 36f666ec-9c43-4c1d-99eb-bad0390775ce · outbound

This paper cites an unresolved cited work.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Unresolved cited work

Reference 67

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:06:31.054273Z

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.

source=pdf_text observed=2026-08-07T12:06:28.850340Z digest=sha256:3ce81b226f47043987ef248303d9aec270ac3876014a2fe413a752e4e14d796a

Observation 6cbed492-fb58-4134-b8be-03d59857c0bd · outbound

This paper cites an unresolved cited work.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Unresolved cited work

Reference 68

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:06:30.859109Z

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.

source=pdf_text observed=2026-08-07T12:06:28.942262Z digest=sha256:c80d7206141dae668323ff9e1d7c283f8a3288c79a3bca71b0d2be7377e27eff

Observation 183b04b1-6345-4137-a9a0-690b40401d62 · outbound

This paper cites an unresolved cited work.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Unresolved cited work

Reference 69

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:06:30.717648Z

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.

source=pdf_text observed=2026-08-07T12:06:29.054286Z digest=sha256:0bb614f4095b6f5fa0f503d0c0047eb66ba1d056d2f5aff73f9e60f1b343400e

Observation 2795bfcc-fc95-4dff-ae5c-784b9e43aebb · outbound

This paper cites search for torrents of XX software,.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents search for torrents of XX software,

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:06:30.471183Z

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.

source=pdf_text observed=2026-08-07T12:06:29.178864Z digest=sha256:8442d75b6bc29893e81fbd53f35ce6ecc6f729a421b6225a5b82f9902d646d0b

Observation a45d0440-976c-4e5e-8665-e7ae6e32256e · outbound

This paper cites an unresolved cited work.

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Unresolved cited work

Reference 2024

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:06:34.199553Z

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.

source=pdf_text observed=2026-08-07T12:06:22.958493Z digest=sha256:56f3db83a76d331f57fe661711adedc5c7f146ece09760c3550e5a2be7343b38

Pith citing papers

Observation e1f0af57-0761-4a52-8269-243c52467e34 · inbound

Interaction as Intelligence: Deep Research With Human-AI Partnership cites this paper.

Interaction as Intelligence: Deep Research With Human-AI Partnership RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 95

Resolution
unresolved
no resolver link, observed 2026-08-06T15:30:41.349884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:30:41.349884Z digest=sha256:6674fa6e8ce956769b998d72f04ffa61476133e9d619b9af31c65d13f2ddc1e7

Observation e02f4beb-6747-45b5-a515-3a32c537d92a · inbound

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them cites this paper.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.600377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.600377Z digest=sha256:108769d88cff1c6183404e81fc1434bd384369d5088c906a092c8b6ac60e7dda

Observation 9eb42b5c-89f6-4424-aa0b-9c329848fb7f · inbound

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows cites this paper.

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-15T15:46:06.025109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T15:46:06.025109Z digest=sha256:c57dbb9a9fbd01487e8e33e224efd05e3ac23b6922291606c4e289e48352c8cf

Observation 198f2fce-0baa-458a-a94e-b9c340a9c42c · inbound

RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management cites this paper.

RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 56

Resolution
verified exact
arxiv_id, observed 2026-05-10T13:45:28.535266Z

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.

source=pdf_text observed=2026-05-10T13:40:55.540869Z digest=sha256:df66ce7be566ce1115a2d8b6d5902420f748e648d446d4d7d308c157075ac4e4

Observation 4f14a556-c514-44ac-ade0-270597fdf455 · 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 RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-11T04:35:56.403952Z

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.

source=pdf_text observed=2026-05-11T01:15:19.239355Z digest=sha256:0c75e72e8b37ab1ce7ac4919450224ed399cc7b240f470a10be23a830a4c7f88

Observation 2bd2be58-e9cb-47bf-9b50-bbe51e238bf6 · inbound

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents cites this paper.

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-11T04:00:56.737761Z

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.

source=pdf_text observed=2026-05-11T02:00:17.765986Z digest=sha256:5e11809021a3357d240627c803f7ad6bc93914c279894cd2d5c7b88b7e4cb718

Observation 08533699-b62e-4b8c-9fd0-ff7e54baaf87 · inbound

ProjGuard: Safety Monitoring for Computer-Use Agents via Low-Dimensional Projections cites this paper.

ProjGuard: Safety Monitoring for Computer-Use Agents via Low-Dimensional Projections RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 33

Resolution
verified exact
arxiv_id, observed 2026-06-30T21:15:04.158298Z

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.

source=pdf_text observed=2026-06-30T21:12:50.686474Z digest=sha256:8036b52322c7b2133bc72c0f4127859ec7b7bb87c30d4f15066ab69b1a412e8e

Observation 8440b821-8599-4093-98be-be1f3d70b564 · inbound

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks cites this paper.

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 99

Resolution
verified exact
arxiv_id, observed 2026-06-30T07:14:21.161346Z

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.

source=pdf_text observed=2026-06-30T07:10:38.909339Z digest=sha256:aea4132135da74f12b7e190f5b907858c38ebad471eddaa0b164687dc85ac7ab

Observation 53b68dca-4d98-4e7b-a568-5e48b6d6d008 · inbound

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks cites this paper.

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 99

Resolution
unresolved
no resolver link, observed 2026-07-15T10:24:53.345620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-15T10:24:53.345620Z digest=sha256:0dc8ca263e9a19446e40435598f4410638d2e81d6b97b03cfe7b2735261c917d

Observation 515df8a8-1794-4b4b-8e36-3b00d246e64a · inbound

AutoTrainess: Teaching Language Models to Improve Language Models Autonomously cites this paper.

AutoTrainess: Teaching Language Models to Improve Language Models Autonomously RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-07-01T10:15:44.751236Z

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.

source=pdf_text observed=2026-07-01T05:39:48.575174Z digest=sha256:bd838906baa6bcdd6aed5f902bc84cd587a5cc94395db36b82dff53fe94c5549