AI RESEARCH
RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution
arXiv CS.LG
•
ArXi:2605.00798v1 Announce Type: new Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multi-agent plan execution platform that interprets natural-language plans while enforcing stepwise execution through constraints and rubrics. RunAgent bridges the expressiveness of natural language with the determinism of programming via an agentic language with explicit control constructs (e.g., \texttt{IF}, \texttt{GOTO}, \texttt.