Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-13T01:19:32.406859Z
Paper Citation Record · LEDGER
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
As of 7 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 100 inbound Pith citation observations for arXiv:2404.07972.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T14:06:57.471803Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
68 of 68 outbound references displayed
- verified exact42
- verified fuzzy15
- unresolved1
- parse uncertain0
- malformed identifier2
- metadata mismatch8
External citation measurements
5
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation e87cf1fd-a8e3-4ed9-88a3-6f9f149cb93f · outbound
This paper cites ACT-1: Transformer for Actions.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ACT-1: Transformer for Actions
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.622324Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 24b03bd5-ccdd-4702-a2b7-7efb120eb987 · outbound
This paper cites Introducing the next generation of claude.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Introducing the next generation of claude
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.615361Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3c6ab962-88a4-44e4-be8a-5adeeefcee2a · outbound
This paper cites The claude 3 model family: Opus, sonnet, haiku.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments The claude 3 model family: Opus, sonnet, haiku
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.612990Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation efc94861-acd1-47a8-ac82-95857e7e65c7 · outbound
This paper cites ScreenAI: A Vision-Language Model for UI and Infographics Understanding.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.469196Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d3d84067-01f8-40ea-a830-988413575bc7 · outbound
This paper cites Qwen Technical Report.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Qwen Technical Report
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.442790Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f0b874fe-07af-41dd-96cf-1ece28c77511 · outbound
This paper cites RT-1: Robotics Transformer for Real-World Control at Scale.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments RT-1: Robotics Transformer for Real-World Control at Scale
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.446816Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 37a39ef4-f617-4a6d-abd2-6c000a0eaf42 · outbound
This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.450810Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 845927e9-9ff1-4b9b-b3fa-45c2748c6dd9 · outbound
This paper cites SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T10:09:46.778093Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 47fc6f52-90de-4566-8eef-4db63cee2c0e · outbound
This paper cites Mind2Web: Towards a Generalist Agent for the Web.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Mind2Web: Towards a Generalist Agent for the Web
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:05:16.335224Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5a5208d7-d8f2-404f-adeb-0f7d94e205c8 · outbound
This paper cites WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T02:48:05.307585Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2b30dd0c-3f10-46f4-a9bc-d16263bd24b1 · outbound
This paper cites an unresolved cited work.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-05-13T01:19:32.607565Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 26bbebfe-935e-4e7b-a189-b2f04b35bbe8 · outbound
This paper cites Multimodal Web Navigation with Instruction-Finetuned Foundation Models.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Multimodal Web Navigation with Instruction-Finetuned Foundation Models
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.525521Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c3821a82-c34f-4022-a157-b50f5a7fa60e · outbound
This paper cites ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.528636Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c4eac973-4ba2-4188-a9fb-89b51cebdd30 · outbound
This paper cites PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.532136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3a4cc4f2-a11f-439c-ac7a-26463c39fa5f · outbound
This paper cites A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T04:37:34.727630Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 640615f0-63c6-4dab-8214-f12642c0eb00 · outbound
This paper cites WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T22:43:35.479641Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 639bd103-164a-48a4-bd0d-82cbf0daa853 · outbound
This paper cites CogAgent: A Visual Language Model for GUI Agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments CogAgent: A Visual Language Model for GUI Agents
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.465423Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 83df3bdd-e0a0-4eec-afb2-4a140ab0c40c · outbound
This paper cites A data-driven approach for learning to control computers.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments A data-driven approach for learning to control computers
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.624649Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0b1d778c-6d22-4137-8a89-1f50763bdee9 · outbound
This paper cites Mixtral of Experts.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Mixtral of Experts
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.541679Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 23455256-bf66-4abe-8213-a40fefe12952 · outbound
This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.545200Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e815a620-7508-4d43-9732-deac89b7ccc0 · outbound
This paper cites OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.548729Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 92394b64-b147-4b23-aa4e-831a1940f237 · outbound
This paper cites VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T15:20:36.653799Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ed91c05c-c1a2-4a65-8ef0-70d490ed9293 · outbound
This paper cites Pix2struct: Screenshot parsing as pretraining for visual language understanding.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Pix2struct: Screenshot parsing as pretraining for visual language understanding
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.635957Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 12a5dd74-81c7-41d0-b5c7-26816fe11cc2 · outbound
This paper cites Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.554838Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0f99749b-d19f-48cd-8994-b69744a70545 · outbound
This paper cites SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models
Reference 25
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.558195Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 233cdd86-cc0c-4292-a444-a54f32b7ff39 · outbound
This paper cites Silkie: Preference Distillation for Large Visual Language Models.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Silkie: Preference Distillation for Large Visual Language Models
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.561482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7e22006b-03c2-44ec-83c9-8832f1ef955c · outbound
This paper cites Mapping Natural Language Instructions to Mobile UI Action Sequences.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Mapping Natural Language Instructions to Mobile UI Action Sequences
Reference 27
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.564185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b4d586ca-ac0c-479e-9abf-d93c0ead8359 · outbound
This paper cites Natasha Chrissane Lobo, Himani H.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Natasha Chrissane Lobo, Himani H
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.434145Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5b082a34-97f9-43d2-918d-30cdbf24c15c · outbound
This paper cites NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.567035Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 24a9e56a-825c-4ac6-87da-d6ccf2b2e8e0 · outbound
This paper cites Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.570023Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9a485cf8-67e6-4daf-879e-b0f154d78f8c · outbound
This paper cites Visual Instruction Tuning.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Visual Instruction Tuning
Reference 31
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.572521Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 67eee199-5d51-4931-bb48-93df08cc5274 · outbound
This paper cites AgentBench: Evaluating LLMs as Agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments AgentBench: Evaluating LLMs as Agents
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.575725Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0d395331-a1c3-4a85-95d2-fe597026794d · outbound
This paper cites Weblinx: Real-world website navigation with multi-turn dialogue.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Weblinx: Real-world website navigation with multi-turn dialogue
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.578740Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f76ff87a-3d72-4686-8967-5ffdc37f8e4c · outbound
This paper cites AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
Reference 34
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.581967Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ed603c44-1608-46e4-8b74-6f233d56c14e · outbound
This paper cites Introducing meta Llama 3: The most capable openly available LLM to date, April.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Introducing meta Llama 3: The most capable openly available LLM to date, April
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.633727Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 42d7b803-cec1-40c0-92f4-f1c27e04127b · outbound
This paper cites Accessed: 2024-04-18.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Accessed: 2024-04-18
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.637770Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b9417b89-2f7a-4391-aa5e-be5c25c69c4e · outbound
This paper cites GAIA: a benchmark for General AI Assistants.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments GAIA: a benchmark for General AI Assistants
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.584711Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a7e8feae-bdba-4547-ab11-e79a45a4179d · outbound
This paper cites WebGPT: Browser-assisted question-answering with human feedback.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments WebGPT: Browser-assisted question-answering with human feedback
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.587578Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6562f1dd-626a-405a-9b2c-07441364ccea · outbound
This paper cites ScreenAgent: A Vision Language Model-driven Computer Control Agent.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ScreenAgent: A Vision Language Model-driven Computer Control Agent
Reference 39
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.591004Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9cb6cda8-7862-40f7-bddc-353dacf7354b · outbound
This paper cites GPT-4 Technical Report.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments GPT-4 Technical Report
Reference 40
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.593875Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 62f91ddf-75f1-4bd0-9b39-51f2e90c0322 · outbound
This paper cites Android in the Wild: A Large-Scale Dataset for Android Device Control.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Android in the Wild: A Large-Scale Dataset for Android Device Control
Reference 41
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.597044Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a6a85c12-7bab-4b87-b114-da4a0822f6f6 · outbound
This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Reference 42
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.600721Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8c1ec10a-7474-423f-9a02-7857a3055474 · outbound
This paper cites An empirical study & evaluation of modern {CAPTCHAs}.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments An empirical study & evaluation of modern {CAPTCHAs}
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.626988Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6b85d019-4022-467c-a17c-d13338099204 · outbound
This paper cites From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
Reference 44
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.604987Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f1f25d28-b1e9-4974-ae04-ce95df3823d7 · outbound
This paper cites World of bits: An open-domain platform for web-based agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments World of bits: An open-domain platform for web-based agents
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.631174Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 43ba48cc-ed59-4645-90a3-6f6c49e8bd51 · outbound
This paper cites Design2code: How far are we from automating front-end engineering?.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Design2code: How far are we from automating front-end engineering?
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.639703Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ae375c20-1860-4380-bebc-47473217e6e9 · outbound
This paper cites Hierarchical Prompting Assists Large Language Model on Web Navigation.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Hierarchical Prompting Assists Large Language Model on Web Navigation
Reference 47
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.472256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 72d4933d-b12f-4ed8-9cf4-9e3dbfffbb68 · outbound
This paper cites META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI
Reference 48
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.475665Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3dbbd82f-cbc1-4881-838f-499ed3fed62c · outbound
This paper cites Cradle: Empowering Foundation Agents Towards General Computer Control.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Cradle: Empowering Foundation Agents Towards General Computer Control
Reference 49
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.478918Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4800fce6-aa93-4591-bbd2-83312df9c5f3 · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Gemini: A Family of Highly Capable Multimodal Models
Reference 50
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.482620Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 27243d42-c013-4d38-9b78-8e8a3ca53f0f · outbound
This paper cites AndroidEnv: A Reinforcement Learning Platform for Android.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments AndroidEnv: A Reinforcement Learning Platform for Android
Reference 51
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.485919Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c39cb77a-d7c0-4023-9b23-4ec4fb37272b · outbound
This paper cites UGIF: UI Grounded Instruction Following.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments UGIF: UI Grounded Instruction Following
Reference 52
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.490386Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7d4aba06-231e-4667-bfdf-ddc9ca440267 · outbound
This paper cites Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
Reference 53
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T00:19:28.048419Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation feede790-49c5-4d60-8560-df638d65c377 · outbound
This paper cites AutoDroid: LLM-powered Task Automation in Android.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments AutoDroid: LLM-powered Task Automation in Android
Reference 54
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.497484Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2e60b7d9-e453-49f4-a766-70025ed83707 · outbound
This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
Reference 55
- Resolution
- malformed identifier
- doi_truncated, observed 2026-05-13T01:19:32.437346Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1cbfd6e8-54ac-4c04-bb7a-bed3622f7ecf · outbound
This paper cites GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation
Reference 56
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.500326Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e14ca917-fbb4-4c6b-b54e-b0a838ad929c · outbound
This paper cites Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Reference 57
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.503391Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4e88b8a0-fefd-425c-8f95-4aee49b6af53 · outbound
This paper cites InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
Reference 58
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.507302Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 764786b0-f6f2-4864-bfdf-3f1703ee23d2 · outbound
This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Webshop: Towards scalable real-world web interaction with grounded language agents
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.641863Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4213af39-1902-4d97-9c4b-8f2ab1274964 · outbound
This paper cites UFO: A UI-Focused Agent for Windows OS Interaction.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments UFO: A UI-Focused Agent for Windows OS Interaction
Reference 60
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.510117Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 64c90358-97b4-4c97-8592-884c8405262b · outbound
This paper cites Appagent: Multimodal agents as smartphone users.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Appagent: Multimodal agents as smartphone users
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.617660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f07dabaf-84a0-4a60-a6ef-c1db6abd67e7 · outbound
This paper cites Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction
Reference 62
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.513206Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a00b3e49-e9e3-4285-8762-0d6e6b0c7d32 · outbound
This paper cites Large language models are semi-parametric reinforcement learning agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Large language models are semi-parametric reinforcement learning agents
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.629086Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 19d6f11c-6204-4b84-9921-77b95068b8ab · outbound
This paper cites You only look at screens: Multimodal chain-of-action agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments You only look at screens: Multimodal chain-of-action agents
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.610216Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1f9b0c30-bc9e-4c26-9274-16972c236550 · outbound
This paper cites Tie: Topological information enhanced structural reading comprehension on web pages.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Tie: Topological information enhanced structural reading comprehension on web pages
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T01:19:32.620251Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e91e920a-ed79-432e-b80b-fa8bd9a595bb · outbound
This paper cites GPT-4V(ision) is a Generalist Web Agent, if Grounded.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments GPT-4V(ision) is a Generalist Web Agent, if Grounded
Reference 66
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T19:40:14.169994Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 55e8ff2e-054e-4603-b32e-b7f878eff23e · outbound
This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments WebArena: A Realistic Web Environment for Building Autonomous Agents
Reference 67
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:19:32.519332Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 78c207b4-616f-4c9c-9242-06017dc48947 · outbound
This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Reference 68
- Resolution
- malformed identifier
- local_arxiv, observed 2026-05-13T01:19:32.522499Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Pith citing papers
Observation 45ea4ba0-8ec6-4a0d-ab76-d0b674236c40 · inbound
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security cites this paper.
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 105
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T00:57:26.848568Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c16d6729-7ab8-46b5-a2b8-dd7129eb580a · inbound
AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents cites this paper.
AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 33
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T12:06:13.844846Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5bd9de76-5195-4c14-9699-a4e4fd35a489 · inbound
WebCanvas: Benchmarking Web Agents in Online Environments cites this paper.
WebCanvas: Benchmarking Web Agents in Online Environments OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 33
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T11:29:14.970132Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 37237622-eb7b-46d3-9022-4158bb0f1338 · inbound
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents cites this paper.
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 69
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-13T09:29:27.553165Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7e9468d6-8aba-438c-8163-6259e7782567 · inbound
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction cites this paper.
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 113
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T04:09:41.649412Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3665c22e-0717-461b-b0bb-7f9dec2a447c · inbound
A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions cites this paper.
A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 173
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T05:02:35.561245Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1dffd54f-cb0c-4994-b4ac-68bbdd7cb12c · inbound
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks cites this paper.
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 52
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-17T21:32:18.687785Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a935f98a-3274-46e4-9fc8-32e1a2850359 · inbound
SWE-smith: Scaling Data for Software Engineering Agents cites this paper.
SWE-smith: Scaling Data for Software Engineering Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-15T10:22:06.984822Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e4804db6-1420-4297-ba88-d5c0bbe94f67 · inbound
Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking cites this paper.
Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T14:06:57.471803Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e54719fc-d061-4af5-b4c3-0d10d14eea7c · inbound
Self-Challenging Language Model Agents cites this paper.
Self-Challenging Language Model Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:40:58.052425Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ba39a1fd-be63-4687-abeb-baa85f06085d · inbound
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback cites this paper.
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:30:56.287971Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a4dbe174-a48d-4b6f-b2f3-a242b1104d8a · inbound
A Red Teaming Roadmap Towards System-Level Safety cites this paper.
A Red Teaming Roadmap Towards System-Level Safety OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 93
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:11:25.259960Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bb747de6-b1f3-453e-8a2f-ccdbc3835f84 · inbound
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities cites this paper.
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:02:29.285064Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e082b267-d4f3-424e-adf6-f4a1d9132bfd · inbound
Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards cites this paper.
Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T04:16:08.492855Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bc31b950-ecb2-4d67-aa18-e3b9c59d6dfd · inbound
Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents cites this paper.
Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:41:18.569925Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f556dbea-3f9c-4423-b125-323b58224c3e · inbound
Deep Research Agents: A Systematic Examination And Roadmap cites this paper.
Deep Research Agents: A Systematic Examination And Roadmap OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 128
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:26:56.979221Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eac92648-2a35-4996-8114-fa90e82c1a78 · inbound
Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents cites this paper.
Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T22:36:44.585127Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b19a5cd-06d0-4230-b831-f8dc0a7641ca · inbound
Multilingual Multimodal Software Developer for Code Generation cites this paper.
Multilingual Multimodal Software Developer for Code Generation OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 83
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:19:58.348232Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6aaf830b-3ec9-4809-b1b8-55ab9db3030f · inbound
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models cites this paper.
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T16:46:01.738182Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a687a27-e2c6-419d-8403-c693e0e42247 · inbound
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning cites this paper.
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T16:14:04.352421Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 86cee43f-b5a5-47e1-bf96-ee4e1c71595f · inbound
Magentic-UI: Towards Human-in-the-loop Agentic Systems cites this paper.
Magentic-UI: Towards Human-in-the-loop Agentic Systems OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 97
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T11:52:12.346411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0b202f99-2d90-468a-bb16-4eeb23db8f52 · inbound
Instruction Agent: Enhancing Agent with Expert Demonstration cites this paper.
Instruction Agent: Enhancing Agent with Expert Demonstration OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T22:55:20.925734Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8cafdc6-f760-4ca0-9b38-f5bee3d790f5 · inbound
Understanding User Experiences of Computer Use Agents: Design Space and Opportunities for Building Agent UX Prototypes cites this paper.
Understanding User Experiences of Computer Use Agents: Design Space and Opportunities for Building Agent UX Prototypes OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T11:31:10.146970Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 07be4d4d-cc99-4fee-9539-94cc41f6ed51 · inbound
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering cites this paper.
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T11:32:15.101569Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation aa8ca01e-9cc6-4fbd-9d53-a162f0550e2c · inbound
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training cites this paper.
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T12:10:24.865140Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d97c84ab-9c89-45ed-be05-c2d32f2cf919 · inbound
StepShield: When, Not Whether to Intervene on Rogue Agents cites this paper.
StepShield: When, Not Whether to Intervene on Rogue Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:48:32.428948Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 904a1599-9831-48bb-94b2-36ee6e0795b0 · inbound
MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers cites this paper.
MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-16T08:30:45.607360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 71f09531-1f2b-40d1-bb63-9db123bdb778 · inbound
MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers cites this paper.
MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T15:10:16.464451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e5540bf1-04d1-4ece-bd63-ead3acd460e1 · inbound
Kimi K2.5: Visual Agentic Intelligence cites this paper.
Kimi K2.5: Visual Agentic Intelligence OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 76
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation fc6ada6d-7735-42f7-a4ac-6ac66b0584ba · inbound
ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System cites this paper.
ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T23:32:14.009549Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a91f53af-6f4a-4505-a425-5dca60de01fa · inbound
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents cites this paper.
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 62
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T23:19:31.260996Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation abcc432b-10f2-4292-80d0-40da3a898ca6 · inbound
Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI cites this paper.
Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T10:21:23.252058Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8c213217-51ad-4a18-8c99-a06869988851 · inbound
AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning cites this paper.
AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T06:49:49.335166Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 298b6312-b1f0-4571-95a8-d2461734e9fc · inbound
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments cites this paper.
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 54
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T01:23:27.095484Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8633bda4-be3a-45df-84ff-f2516609ef69 · inbound
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents cites this paper.
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 44285b12-253b-4eb4-a757-3f1a25d360d0 · inbound
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents cites this paper.
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T07:00:27.121649Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 40057c14-2a2d-40d2-ba8a-dc9ed847dd4d · inbound
FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks cites this paper.
FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2398afb7-84a7-4154-aee6-5a595908d505 · inbound
Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems cites this paper.
Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 032d5d0a-5811-4825-a3f9-abe5baaeae9f · inbound
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web cites this paper.
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 66
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cc198b38-781f-46a9-af33-525685b05aeb · inbound
SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment cites this paper.
SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ecc082ca-81bb-41b2-aee2-eddc131da08c · inbound
SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment cites this paper.
SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T23:36:55.286437Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d2c8c00-37d3-4151-941b-2e26111b9c2e · inbound
ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents cites this paper.
ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 45
- Resolution
- malformed identifier
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ee85e413-d8c0-4d3b-8823-d78918b9f5f4 · inbound
AlphaEval: Evaluating Agents in Production cites this paper.
AlphaEval: Evaluating Agents in Production OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 49a3dcac-b105-4d31-93ad-642ccc14491b · inbound
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models cites this paper.
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c6e0dfde-0040-4693-b42e-d6b1c9497225 · inbound
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models cites this paper.
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T20:25:41.773345Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation acf8215c-e671-43dd-b4bf-76b79fdcf04b · inbound
Beyond Chat and Clicks: GUI Agents for In-Situ Assistance via Live Interface Transformation cites this paper.
Beyond Chat and Clicks: GUI Agents for In-Situ Assistance via Live Interface Transformation OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 54
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b2fd0831-55c3-4b44-bcee-94bf73eab6a7 · inbound
Feedback-Driven Execution for LLM-Based Binary Analysis cites this paper.
Feedback-Driven Execution for LLM-Based Binary Analysis OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 47
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bcd0509b-45db-4e80-9215-df0592d69242 · inbound
MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs cites this paper.
MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 58
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1a843195-225a-4412-b517-bfb9ca7bb020 · inbound
AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum cites this paper.
AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3087765e-665b-4789-80c0-4b10fa6ad09d · inbound
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence cites this paper.
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 114
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1c2be504-a7cd-435b-aa65-7e1cada043de · inbound
An AI Agent Execution Environment to Safeguard User Data cites this paper.
An AI Agent Execution Environment to Safeguard User Data OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 73
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9c3fde8a-7c01-4147-8f95-ec5d9399ff71 · inbound
Addressing the Reality Gap: A Three-Tension Framework for Agentic AI Adoption cites this paper.
Addressing the Reality Gap: A Three-Tension Framework for Agentic AI Adoption OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 56
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 39a0e033-0990-49a6-a3da-4e8240976b5d · inbound
Addressing the Reality Gap: A Three-Tension Framework for Agentic AI Adoption cites this paper.
Addressing the Reality Gap: A Three-Tension Framework for Agentic AI Adoption OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 56
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T23:53:51.353667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c8618001-0809-4a68-9bfe-fae470de5136 · inbound
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles cites this paper.
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2be37d84-b3eb-4d9f-8621-3abdc73dea44 · inbound
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles cites this paper.
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T06:59:49.257627Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7ee0a034-8c83-48a4-ad06-a7a32eebe56d · inbound
Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents cites this paper.
Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 312c40f5-f571-4b74-84e4-f205ae9638df · inbound
X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction cites this paper.
X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e090455c-764d-4059-bba2-527dd17e2491 · inbound
X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction cites this paper.
X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:51:21.719603Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7fe53c18-0841-40f0-9444-da361312a449 · inbound
From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work cites this paper.
From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cccaf9a3-0569-44c7-954e-1a197f8918cd · inbound
Computer Use at the Edge of the Statistical Precipice cites this paper.
Computer Use at the Edge of the Statistical Precipice OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 19
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ec5fb971-a6ec-4eb9-9ade-2d989e18b270 · inbound
Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation cites this paper.
Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 25
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 91415c43-8a4a-4889-a950-cf58d03451d3 · inbound
MMTB: Evaluating Terminal Agents on Multimedia-File Tasks cites this paper.
MMTB: Evaluating Terminal Agents on Multimedia-File Tasks OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T01:19:32.642608Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 129bda9f-d70a-4730-97fc-d03263e9b001 · inbound
Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack cites this paper.
Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 58
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T20:32:56.835280Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 628d2910-eb0e-44f0-a840-a01d93968117 · 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 OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T21:15:04.178212Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bb2eabd7-0d48-4ba9-8e92-d94058ae0a1b · inbound
ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation cites this paper.
ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T05:19:46.267389Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 17efd460-2324-4a42-8f49-25ed16f9ddc7 · inbound
ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation cites this paper.
ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T20:33:43.129581Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a9b79432-6d19-41d0-9b3b-99d0ea5a0813 · inbound
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows? cites this paper.
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows? OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 60
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T17:48:48.826044Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 485adf21-7650-4e82-b235-0a94a4437746 · inbound
TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents cites this paper.
TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T22:57:50.193076Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 92dbda9f-7b41-44f9-9101-2dd726c6d696 · inbound
MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding cites this paper.
MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T22:12:50.568653Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c4b78e58-b813-4555-bd31-05a4205fa2c4 · inbound
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows cites this paper.
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 50
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T10:18:11.662722Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f04903dd-771d-4f29-b4d4-5a70e275a4c1 · inbound
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 87
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T05:51:08.002848Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b4444d1a-6104-4618-8ef6-77bc024d2374 · inbound
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 87
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T06:06:42.834544Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e875bef5-035f-4dc6-9d21-f8bc8f663f7a · inbound
ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis cites this paper.
ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T11:04:37.692134Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ba4257a2-04d5-4132-b839-2a476e23b5a1 · inbound
Toward Native Multimodal Modeling: A Roadmap cites this paper.
Toward Native Multimodal Modeling: A Roadmap OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 133
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T23:04:01.790934Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0b9f29b5-77bb-4699-ae9e-568309c91f0d · inbound
VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents cites this paper.
VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T14:54:45.652180Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b538d906-a148-4471-a20c-adb3ef165141 · inbound
JobBench: Aligning Agent Work With Human Will cites this paper.
JobBench: Aligning Agent Work With Human Will OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T21:33:59.457856Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b7054e13-65f4-4ff1-9991-a6e79549a425 · inbound
OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents cites this paper.
OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T12:53:26.367017Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 99d73b7a-c0c8-4b2f-9ff9-874eff3809cc · inbound
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis cites this paper.
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 6
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-29T16:13:36.055090Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 431c9706-c82f-443a-a499-cd75dff39cc1 · inbound
unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning cites this paper.
unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T11:23:20.863611Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d25a1708-869f-4877-94de-43d5f06fc7b7 · inbound
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models cites this paper.
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 75
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T23:06:21.120068Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 204f3772-d73c-4ebd-819c-6a34d06aa610 · inbound
Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming cites this paper.
Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 21
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T08:06:48.247592Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5bfbde66-5caf-4e99-b9d3-61db7a082ccc · inbound
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments cites this paper.
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T12:56:56.823942Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 59e18fa3-dd0c-40fd-becf-acb2b4d70162 · inbound
DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions cites this paper.
DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 6
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-28T01:41:29.382021Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 986ea443-d739-45f7-a4bd-2a2424c8ba3d · inbound
Signal-Driven Observation for Long-Horizon Web Agents cites this paper.
Signal-Driven Observation for Long-Horizon Web Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-06-28T01:31:29.182702Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f471f672-402a-4c1f-9f79-c3c8f5afc7ce · inbound
Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents cites this paper.
Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 4
- Resolution
- malformed identifier
- local_arxiv, observed 2026-06-27T19:51:12.581395Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 676eedc4-f966-46ac-8a5a-bf48f9198938 · inbound
Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces cites this paper.
Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T00:37:29.834859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9034f7da-dcdf-4ee1-8b55-ce51053694db · inbound
MedCTA: A Benchmark for Clinical Tool Agents cites this paper.
MedCTA: A Benchmark for Clinical Tool Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 68
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T09:07:47.973992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ecdfb51e-749b-4c1c-8f12-830a4a1967d5 · inbound
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails cites this paper.
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T16:58:43.570651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b0e318c6-2350-4f65-9b7f-ef12c8db6307 · inbound
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence cites this paper.
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 87
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T17:38:44.116785Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4c6f4af5-c226-4b7d-8677-afe15c476945 · inbound
ProCUA-SFT Technical Report cites this paper.
ProCUA-SFT Technical Report OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T18:08:46.692464Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 20c23fbe-6d3a-4871-b31f-22cbee475275 · inbound
Dissecting model behavior through agent trajectories cites this paper.
Dissecting model behavior through agent trajectories OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 50
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T20:18:56.935465Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9fba41a5-172a-477f-9198-c5c2054a91e0 · inbound
EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning cites this paper.
EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T20:18:57.201947Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b24081f8-6507-4cb3-9fc4-6f529091bc0f · inbound
OpenRath: Session-Centered Runtime State for Agent Systems cites this paper.
OpenRath: Session-Centered Runtime State for Agent Systems OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 45
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T01:29:23.057631Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 634fb884-4b43-4c52-a1ac-aa63bb85ae65 · inbound
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns cites this paper.
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 60
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T02:19:23.924611Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a61e9752-141a-4f5f-9513-355acb2bed54 · inbound
MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents cites this paper.
MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 8
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T21:08:58.347763Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b8cde36b-ff87-4f3a-9bd5-2d4efbadff3e · inbound
PhoneBuddy: Training Open Models for Agentic Phone Use cites this paper.
PhoneBuddy: Training Open Models for Agentic Phone Use OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 21
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T10:59:46.504700Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ed6c4d3c-cf0f-4a99-8330-cd5ab95518ac · inbound
Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents cites this paper.
Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T11:37:35.542449Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 90aa53f0-1a45-4f9c-988b-3726014708b1 · inbound
Agent-Computer Observation Interfaces Enable Dynamic Computer Use cites this paper.
Agent-Computer Observation Interfaces Enable Dynamic Computer Use OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T07:04:21.271037Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bc1ea22f-ce92-4b19-bd9c-78e4d25964e6 · 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 OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 91
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T07:14:21.100795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 958cd20e-c09a-4896-b797-a35e52443aa0 · 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 OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Reference 91
- Resolution
- unresolved
- no resolver link, observed 2026-07-15T10:24:53.345620Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.