OSWorld provides the first unified real-computer benchmark for open-ended multimodal agent tasks, exposing large performance gaps between humans and state-of-the-art LLM/VLM agents.
hub Canonical reference
Weblinx: Real-world website navigation with multi-turn dialogue
Canonical reference. 80% of citing Pith papers cite this work as background.
17
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
dataset 1
citation-polarity summary
representative citing papers
Skim profiles website patterns offline to enable fast-path speculative execution for web agents, cutting median cost by 1.9x and latency by 33.4% with no accuracy loss on benchmarks.
A parallel multi-turn medical dialogue dataset spanning English and nine Indic languages is created from synthetic consultations to enable personalized AI healthcare interactions.
ViBR reproduces 72% of bugs from video reports by segmenting actions with CLIP similarity and using VLMs for region-aware GUI state comparison, outperforming prior heuristics-based methods.
Open 4B and 8B visual web agents achieve state-of-the-art results on browser benchmarks by predicting actions from screenshots and instructions, outperforming similar open models and some closed larger-model agents, with full release of data and code planned.
EconWebArena is a new benchmark with 360 curated economic tasks across 82 authoritative websites for evaluating multimodal web agents on navigation, grounding, and data extraction.
WorkArena benchmark shows LLM web agents achieve partial success on enterprise tasks but have a substantial gap to full automation and perform worse with open-source models.
OSWorld 2.0 is a benchmark of 108 realistic long-horizon computer-use tasks where current agents achieve only 20.6% binary completion, struggling with state inference and constraint tracking.
VLAA-GUI adds mandatory visual verifiers, multi-tier loop breakers, and on-demand search to GUI agents, reaching 77.5% on OSWorld and 61.0% on WindowsAgentArena with some models exceeding human performance.
WebChain supplies the largest open dataset of real human web trajectories with triple-modal alignment and a dual mid-training method that separates grounding from planning to improve web agents.
Aguvis presents a pure vision-based framework for autonomous GUI agents using structured reasoning via inner monologue, a new multimodal dataset, and two-stage training to reach SOTA on offline and online benchmarks.
WebCanvas creates a dynamic benchmark for web agents with a noise-resistant evaluation metric, the Mind2Web-Live dataset of 542 tasks, and open-source tools and agent framework for ongoing online testing.
Parallel WebBench reveals GRPO training raises web agent completion to 96% but leaves a large correctness gap from context-bound loops, premature termination, and synthesis collapse.
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
A survey categorizing LLM-powered agent systems into software-based, physical, and hybrid types, covering industrial applications and challenges such as latency and security.
citing papers explorer
-
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
OSWorld provides the first unified real-computer benchmark for open-ended multimodal agent tasks, exposing large performance gaps between humans and state-of-the-art LLM/VLM agents.
-
Skim: Speculative Execution for Fast and Efficient Web Agents
Skim profiles website patterns offline to enable fast-path speculative execution for web agents, cutting median cost by 1.9x and latency by 33.4% with no accuracy loss on benchmarks.
-
IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages
A parallel multi-turn medical dialogue dataset spanning English and nine Indic languages is created from synthetic consultations to enable personalized AI healthcare interactions.
-
ViBR: Automated Bug Replay from Video-based Reports using Vision-Language Models
ViBR reproduces 72% of bugs from video reports by segmenting actions with CLIP similarity and using VLMs for region-aware GUI state comparison, outperforming prior heuristics-based methods.
-
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Open 4B and 8B visual web agents achieve state-of-the-art results on browser benchmarks by predicting actions from screenshots and instructions, outperforming similar open models and some closed larger-model agents, with full release of data and code planned.
-
EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments
EconWebArena is a new benchmark with 360 curated economic tasks across 82 authoritative websites for evaluating multimodal web agents on navigation, grounding, and data extraction.
-
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
WorkArena benchmark shows LLM web agents achieve partial success on enterprise tasks but have a substantial gap to full automation and perform worse with open-source models.
-
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
OSWorld 2.0 is a benchmark of 108 realistic long-horizon computer-use tasks where current agents achieve only 20.6% binary completion, struggling with state inference and constraint tracking.
-
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
VLAA-GUI adds mandatory visual verifiers, multi-tier loop breakers, and on-demand search to GUI agents, reaching 77.5% on OSWorld and 61.0% on WindowsAgentArena with some models exceeding human performance.
-
WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces
WebChain supplies the largest open dataset of real human web trajectories with triple-modal alignment and a dual mid-training method that separates grounding from planning to improve web agents.
-
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Aguvis presents a pure vision-based framework for autonomous GUI agents using structured reasoning via inner monologue, a new multimodal dataset, and two-stage training to reach SOTA on offline and online benchmarks.
-
WebCanvas: Benchmarking Web Agents in Online Environments
WebCanvas creates a dynamic benchmark for web agents with a noise-resistant evaluation metric, the Mind2Web-Live dataset of 542 tasks, and open-source tools and agent framework for ongoing online testing.
-
When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration
Parallel WebBench reveals GRPO training raises web agent completion to 96% but leaves a large correctness gap from context-bound loops, premature termination, and synthesis collapse.
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
-
LLM-Powered AI Agent Systems and Their Applications in Industry
A survey categorizing LLM-powered agent systems into software-based, physical, and hybrid types, covering industrial applications and challenges such as latency and security.
- Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection
- ClawEnvKit: Automatic Environment Generation for Claw-Like Agents