An LLM agent with three specialized models and execution memory follows text-defined standard operating procedures, achieving 97.8% state-decision accuracy on synthetic e-commerce seller chats with GPT-4o-mini.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Agent-S: LLM Agentic workflow to automate Standard Operating Procedures
An LLM agent with three specialized models and execution memory follows text-defined standard operating procedures, achieving 97.8% state-decision accuracy on synthetic e-commerce seller chats with GPT-4o-mini.