Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T05:33:58.386115Z
Paper Citation Record · LEDGER
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
As of 18 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 12 inbound Pith citation observations for arXiv:2506.07672.
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 2026-08-17T06:30:58.91139+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T16:46:01.921739Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-03T16:58:43.632383Z
Reference resolution
33 of 33 outbound references displayed
- verified exact1
- verified fuzzy18
- unresolved14
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation eaee963a-aa0b-4b5f-8cd0-b53c12bf713c · outbound
This paper cites Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.934356Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation e058cd25-d30f-4b56-8da8-6701a7555d12 · outbound
This paper cites Introduction: Get started with the model context protocol (mcp).
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Introduction: Get started with the model context protocol (mcp)
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.919779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation dceaab9d-650c-4a70-a07b-a634e8efa602 · outbound
This paper cites Meet claude on your desktop.https://claude.ai/download.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Meet claude on your desktop.https://claude.ai/download
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.905409Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation d2b76e7c-03bf-4da4-a1ba-01548684e441 · outbound
This paper cites Windows agent arena: Evaluating multi-modal os agents at scale, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Windows agent arena: Evaluating multi-modal os agents at scale, 2024
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.260760Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6f764a53-b59f-44af-85a9-4ada300ed073 · outbound
This paper cites A3: Android agent arena for mobile gui agents, 2025.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents A3: Android agent arena for mobile gui agents, 2025
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.880983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation e807f8f9-4233-487c-bcf9-4ac7ee8d0a0e · outbound
This paper cites Laradji, Manuel Del Verme, Tom Marty, Léo Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, and Alexandre Lacoste.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Laradji, Manuel Del Verme, Tom Marty, Léo Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, and Alexandre Lacoste
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.269202Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 72881521-7e87-4faf-98c0-e8dc51a3ad41 · outbound
This paper cites Assistgui: Task-oriented desktop graphical user interface automation, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Assistgui: Task-oriented desktop graphical user interface automation, 2024
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.856300Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation eda22142-cf68-44bf-809b-b147cab8e364 · outbound
This paper cites Visualwebarena: Evaluating multimodal agents on realistic visual web tasks, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Visualwebarena: Evaluating multimodal agents on realistic visual web tasks, 2024
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.277591Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e366c75e-1aa1-42a2-a0ec-6a21b2af849b · outbound
This paper cites Benchmarking mobile device control agents across diverse configurations, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Benchmarking mobile device control agents across diverse configurations, 2024
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.831507Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 19b9a591-088b-4388-a78d-0b489a24bd90 · outbound
This paper cites Api-bank: A comprehensive benchmark for tool-augmented llms, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Api-bank: A comprehensive benchmark for tool-augmented llms, 2023
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.286383Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 85903456-8f0e-43f0-a946-3525259a066e · outbound
This paper cites Taskmatrix.ai: Completing tasks by connecting foundation models with millions of apis, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Taskmatrix.ai: Completing tasks by connecting foundation models with millions of apis, 2023
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.290338Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0aa625ee-5d04-429c-b941-8ec062da36c4 · outbound
This paper cites Agentbench: Evaluating llms as agents, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Agentbench: Evaluating llms as agents, 2023
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.294843Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d555a05a-f408-42ab-978b-1da359530623 · outbound
This paper cites Visualagentbench: Towards large multimodal models as visual foundation agents, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Visualagentbench: Towards large multimodal models as visual foundation agents, 2024
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.299023Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8d0c7ad-1906-4a8c-a58a-513240d4ae18 · outbound
This paper cites Gaia: a benchmark for general ai assistants, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Gaia: a benchmark for general ai assistants, 2023
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.303282Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f7e54e52-42bf-4589-98e1-0621f48726a5 · outbound
This paper cites frida: Dynamic instrumentation toolkit for developers, reverse-engineers, and security researchers.https://frida.re/.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents frida: Dynamic instrumentation toolkit for developers, reverse-engineers, and security researchers.https://frida.re/
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.765095Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 336c54e4-858c-4979-b564-d623d567a642 · outbound
This paper cites Toolllm: Facilitating large language models to master 16000+ real-world apis, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Toolllm: Facilitating large language models to master 16000+ real-world apis, 2023
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.311650Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 45ff14a3-a57a-43c5-a0bc-a91213b694d2 · outbound
This paper cites Androidworld: A dynamic benchmarking environment for autonomous agents, 2025.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Androidworld: A dynamic benchmarking environment for autonomous agents, 2025
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.315923Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c7a71f2d-56b2-462e-b732-90c2da61e818 · outbound
This paper cites Toolalpaca: Generalized tool learning for language models with 3000 simulated cases, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Toolalpaca: Generalized tool learning for language models with 3000 simulated cases, 2023
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.730639Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation a4699863-2fea-41c4-8fe5-37f1fbd63fdc · outbound
This paper cites Ducktrack: Multimodal computer agent data collection program.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Ducktrack: Multimodal computer agent data collection program
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.715312Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation ba833b08-c98e-4d4f-bc0f-eb9bc662fc39 · outbound
This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.328670Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e730522f-7e81-4c82-bba1-6ca642d09022 · outbound
This paper cites Understanding the weakness of large language model agents within a complex android environment, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Understanding the weakness of large language model agents within a complex android environment, 2024
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.690933Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 474646de-eea5-41b4-b67c-db4e5196579d · outbound
This paper cites Androidlab: Training and systematic benchmarking of android autonomous agents, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Androidlab: Training and systematic benchmarking of android autonomous agents, 2024
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.674983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation e005db5e-41b7-4b9d-b3a4-fb9a643042a1 · outbound
This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Webshop: Towards scalable real-world web interaction with grounded language agents, 2023
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.660879Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 22a0a3ff-1832-4c9e-8bde-e85a68ae5650 · outbound
This paper cites React: Synergizing reasoning and acting in language models, 2023.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents React: Synergizing reasoning and acting in language models, 2023
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.345316Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4c438cda-01e8-4b1a-b874-36af2ff0dc53 · outbound
This paper cites Llamatouch: A faithful and scalable testbed for mobile ui task automation, 2024.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Llamatouch: A faithful and scalable testbed for mobile ui task automation, 2024
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.635497Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 1911420d-0a32-41f8-8b11-674548479e4c · outbound
This paper cites Agentstudio: A toolkit for building general virtual agents, 2025.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Agentstudio: A toolkit for building general virtual agents, 2025
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.621085Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation da87977c-51db-4378-a477-d799c90c4f25 · outbound
This paper cites Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:33:58.357579Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6cb287dc-b6f9-4df7-bac3-91cbb8dd244d · outbound
This paper cites source=<path_to_executable_on_host>,target=<path_in_container>,type=bind.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents source=<path_to_executable_on_host>,target=<path_in_container>,type=bind
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.594788Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 2ec2dd05-6c23-4b6d-8faa-f99a62b97429 · outbound
This paper cites DISPLAY")} and use a subshell. For example.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents DISPLAY")} and use a subshell. For example
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.579848Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 1eca27e5-444e-42ad-8229-e4068b9a56b9 · outbound
This paper cites an unresolved cited work.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Unresolved cited work
Reference 30
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:33:58.564809Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 9ec3d78b-20f1-4852-85f2-81fe9855ceac · outbound
This paper cites skip this step.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents skip this step
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.548816Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 68a2b53b-8ad2-41cc-967a-ed7c36ac666a · outbound
This paper cites Translate the selected text in this document to French and save it.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents Translate the selected text in this document to French and save it
Reference 32
- Resolution
- verified exact
- raw_fallback, observed 2026-08-07T05:33:58.517409Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 3c11df0d-573b-4c58-89b9-f04efe0b397e · outbound
This paper cites 6 Hard 36 Table 10: List of all tasks inMCPWorld.
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents 6 Hard 36 Table 10: List of all tasks inMCPWorld
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:33:58.533481Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Pith citing papers
Observation 1eb775e8-6a66-43bf-8819-92406bbd28fe · inbound
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models cites this paper.
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T16:46:01.921739Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f7a0d013-03b6-4926-ba85-d75d3e15b9c3 · inbound
A Lightweight Incentive-Based Privacy-Preserving Smart Metering Protocol for Value-Added Services cites this paper.
A Lightweight Incentive-Based Privacy-Preserving Smart Metering Protocol for Value-Added Services MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T18:22:38.827026Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a376052b-e262-43f6-a908-9614e1ff5ffc · inbound
Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning cites this paper.
Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T17:30:53.019433Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 243bc8a0-b7dc-4bf8-b652-ccd629528d4a · inbound
Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible cites this paper.
Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T06:00:40.675891Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 8452a3a0-eee1-4771-b103-ebfb2b7bf7b6 · inbound
Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions cites this paper.
Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 111
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T23:04:39.079613Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4f449e7c-a18d-4988-bc25-02914ce5608a · inbound
EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning cites this paper.
EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T06:31:01.900336Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 8bfd9166-add6-4c7a-82d4-3864fde10f51 · inbound
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox cites this paper.
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T06:01:23.427442Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation f49e1e44-bb4c-4f36-a2b7-306019a8585a · inbound
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox cites this paper.
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T08:09:51.280527Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 261775e9-2254-43bf-88f9-877dfd391f50 · inbound
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents cites this paper.
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 50
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T03:52:12.452282Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation fb7162ca-d5fd-4e02-b581-07cc2e7b2a23 · inbound
From Question Answering to Task Completion: A Survey on Agent System and Harness Design cites this paper.
From Question Answering to Task Completion: A Survey on Agent System and Harness Design MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 147
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T16:58:43.634306Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 54bcb467-5f8b-4bee-8936-51e2332a4f7a · inbound
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents cites this paper.
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T05:06:47.508954Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 38416ba2-78e4-47d3-80f4-95207af0287a · inbound
GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks cites this paper.
GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T22:55:34.013951Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.