RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution (IEEE)

Publication Date: 5/10/2026

Event: IEEE Conference on Artificial Intelligence 2026 (IEEE CAI 2026)

Reference: pp. 1-6, 2026

Authors: Arunabh Srivastava, NEC Laboratories America, Inc.; Mohammad A. Khojastepour, NEC Laboratories America, Inc., University of Maryland, College Park; Giuseppe Coviello, NEC Laboratories America, Inc.; Kunal Rao, NEC Laboratories America, Inc.; Srimat T. Chakradhar, NEC Laboratories America, Inc.; Sennur Ulukus, NEC Laboratories America, Inc., University of Maryland, College Park

Abstract: Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multiagent plan execution platform that interprets natural-language plans while enforcing stepwise execution through constraints and rubrics. RunAgent bridges the expressiveness of natural language and the determinism of programming languages via an agentic language with explicit control constructs (e.g., IF, GOTO, FORALL). It autonomously derives and verifies constraints at each step; dynamically selects among LLM reasoning, tool use, and Python execution; and integrates error correction to ensure correctness. Evaluations on Natural-plan and SciBench Datasets demonstrate that RunAgent outperforms baseline LLMs and state-of-the-art PlanGEN methods.

Publication Link: https://ieeexplore.ieee.org/document/11536499