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

arXiv: https://arxiv.org/abs/2605.00798 · HTML: https://mlsanity.com/paper/2605.00798/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 10 of 10)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [NATURAL PLAN: Benchmarking LLMs on Natural Language Planning](https://mlsanity.com/paper/2406.04520/) (2024)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://mlsanity.com/paper/2507.22358/) (2025)
- [Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents](https://mlsanity.com/paper/2505.09970/) (2025)
- [Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code](https://mlsanity.com/paper/2503.18809/) (2025)
- [PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving](https://mlsanity.com/paper/2502.16111/) (2025)

## Built on by (most cited first, 2 of 2)

- [COVENANT: Natural-Language Workflow Compilation for Aligned Agent Execution](https://mlsanity.com/paper/2607.25400/) (2026)
- [GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI](https://mlsanity.com/paper/2609.30147/) (2026)

## Abstract (arXiv)

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., textttIF, textttGOTO, textttFORALL). 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.