CRMArena-Pro is an expert-validated benchmark showing LLM agents struggle with multi-turn business tasks and confidentiality, with top agents scoring about 58% single-turn and near-zero refusal rates.
Introducing llama 4: Our most advanced models for multimodal intelligence
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions
CRMArena-Pro is an expert-validated benchmark showing LLM agents struggle with multi-turn business tasks and confidentiality, with top agents scoring about 58% single-turn and near-zero refusal rates.