REVIEW 6 cited by
VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Videos are often used to learn or extract the necessary information to complete tasks in ways different than what text and static imagery alone can provide. However, many existing agent benchmarks neglect long-context video understanding, instead focusing on text or static image inputs. To bridge this gap, we introduce VideoWebArena (VideoWA), a benchmark for evaluating the capabilities of long-context multimodal agents for video understanding. VideoWA consists of 2,021 web agent tasks based on manually crafted video tutorials, which total almost four hours of content. For our benchmark, we define a taxonomy of long-context video-based agent tasks with two main areas of focus: skill retention and factual retention. While skill retention tasks evaluate whether an agent can use a given human demonstration to complete a task efficiently, the factual retention task evaluates whether an agent can retrieve instruction-relevant information from a video to complete a task. We find that the best model achieves 13.3% success on factual retention tasks and 45.8% on factual retention QA pairs, far below human performance at 73.9% and 79.3%, respectively. On skill retention tasks, long-context models perform worse with tutorials than without, exhibiting a 5% performance decrease in WebArena tasks and a 10.3% decrease in VisualWebArena tasks. Our work highlights the need to improve the agentic abilities of long-context multimodal models and provides a testbed for future development with long-context video agents.
Forward citations
Cited by 6 Pith papers
-
FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks
A new benchmark dataset and evaluation framework for testing multimodal AI agents on real field work tasks derived from on-site data and worker interviews.
-
Instruction Agent: Enhancing Agent with Expert Demonstration
With one human demonstration, the Instruction Agent extracts instructions and uses verifier/backtracker modules to execute them, reaching 60% success on 20 previously unsolved OSWorld tasks.
-
Build the web for agents, not agents for the web
The paper proposes a paradigm shift: design a standardized Agentic Web Interface for AI agents, rather than adapting agents to human-facing websites.
-
DeepShop: A Benchmark for Deep Research Shopping Agents
DeepShop, a benchmark of 150 complex online shopping queries with fine-grained evaluation, shows that leading web agents and deep research systems achieve at most a 32% task success rate.
-
WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
R1-style reinforcement learning on single-step web actions lifts open-source agents above gpt-4o on WorkArena while avoiding the reward hacking seen with dense rewards.
-
Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
A survey that classifies AI agent evaluation benchmarks along environment and capability axes, and proposes five traits that distinguish agents from chatbots.
Discussion (0). Sign in to comment.