EntCollabBench shows that today's LLM agents still struggle with delegation, context transfer, parameter grounding, workflow closure, and decision commitment when tested in a simulated enterprise with 11 role-specialized agents.
arXiv preprint arXiv:2411.02305
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
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.
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
citing papers explorer
-
Beyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise Workflows
EntCollabBench shows that today's LLM agents still struggle with delegation, context transfer, parameter grounding, workflow closure, and decision commitment when tested in a simulated enterprise with 11 role-specialized agents.
-
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.
-
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.