A new multi-agent framework with payload referencing and dynamic routing reaches 90% goal success on a self-built 90-scenario enterprise benchmark, outperforming a single-agent baseline.
AgentQuest: A modular benchmark framework to measure progress and improve LLM agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications
A new multi-agent framework with payload referencing and dynamic routing reaches 90% goal success on a self-built 90-scenario enterprise benchmark, outperforming a single-agent baseline.