RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Srivastava, Arunabh, A., Mohammad, Khojastepour, Chakradhar, Srimat, Ulukus, Sennur
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910183874101248
author Srivastava, Arunabh
A., Mohammad
Khojastepour
Chakradhar, Srimat
Ulukus, Sennur
author_facet Srivastava, Arunabh
A., Mohammad
Khojastepour
Chakradhar, Srimat
Ulukus, Sennur
contents 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{FORALL}). Beyond verifying syntactic and semantic verification of the step output, which is performed based on the specific instruction of each step, RunAgent autonomously derives and validates constraints based on the description of the task and its instance at each step. RunAgent also dynamically selects among LLM-based reasoning, tool usage, and code generation and execution (e.g., in Python), and incorporates error correction mechanisms to ensure correctness. Finally, RunAgent filters the context history by retaining only relevant information during the execution of each step. Evaluations on Natural-plan and SciBench Datasets demonstrate that RunAgent outperforms baseline LLMs and state-of-the-art PlanGEN methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00798
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution
Srivastava, Arunabh
A., Mohammad
Khojastepour
Chakradhar, Srimat
Ulukus, Sennur
Machine Learning
Computation and Language
Multiagent Systems
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{FORALL}). Beyond verifying syntactic and semantic verification of the step output, which is performed based on the specific instruction of each step, RunAgent autonomously derives and validates constraints based on the description of the task and its instance at each step. RunAgent also dynamically selects among LLM-based reasoning, tool usage, and code generation and execution (e.g., in Python), and incorporates error correction mechanisms to ensure correctness. Finally, RunAgent filters the context history by retaining only relevant information during the execution of each step. Evaluations on Natural-plan and SciBench Datasets demonstrate that RunAgent outperforms baseline LLMs and state-of-the-art PlanGEN methods.
title RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution
topic Machine Learning
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2605.00798