# LLMs for Executable Multi-Agent System Specification Generation

arXiv: https://arxiv.org/abs/2609.34619 · HTML: https://mlsanity.com/paper/2609.34619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 73 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 18 of 18)

- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [Chain of Thoughtlessness? An Analysis of CoT in Planning](https://mlsanity.com/paper/2405.04776/) (2024)
- [Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text](https://mlsanity.com/paper/2307.07696/) (2023)
- [Empowering LLMs with Logical Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2502.15652/) (2025)
- [Large Language Models Miss the Multi-Agent Mark](https://mlsanity.com/paper/2505.21298/) (2025)
- [LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions](https://mlsanity.com/paper/2501.00830/) (2025)
- [Expressive Stream Reasoning with Laser](https://mlsanity.com/paper/1707.08876/) (2017)
- [ChatLogic: Integrating Logic Programming with Large Language Models for Multi-Step Reasoning](https://mlsanity.com/paper/2407.10162/) (2024)
- [Composite Event Recognition for Maritime Monitoring](https://mlsanity.com/paper/1903.03078/) (2019)
- [A Distributed Approach to LARS Stream Reasoning (System paper)](https://mlsanity.com/paper/1907.12344/) (2019)
- [Combining Event Calculus and Description Logic Reasoning via Logic Programming](https://mlsanity.com/paper/2109.04803/) (2021)
- [Are Language Models Efficient Reasoners? A Perspective from Logic Programming](https://mlsanity.com/paper/2510.25626/) (2025)
- [Ticker: A System for Incremental ASP-based Stream Reasoning](https://mlsanity.com/paper/1707.05304/) (2017)
- [CORE: a Complex Event Recognition Engine](https://mlsanity.com/paper/2111.04635/) (2021)

## Abstract (arXiv)

MAS specifications express the effects of the actions of the agents and their environment, as well as other temporal phenomena, such as the intervals during which an agent may perform an action. The specification of a MAS should also be executable in order to allow for run-time monitoring. Constructing the specification of a MAS requires formal language expertise, while machine learning techniques depend on labelled data which are rarely available. To address these issues, we propose `genRTEC', a method that leverages pre-trained Large Language Models (LLMs) to generate executable MAS specifications, in the language of the `Run-Time Event Calculus' (RTEC), from natural language descriptions. genRTEC constructs MAS specifications with complex hierarchical and cyclic dependencies based only on short natural language descriptions of the concepts involved. We present an extensive empirical evaluation of genRTEC, spanning various MAS specifications, including both a qualitative and a quantitative assessment. Our results demonstrate that genRTEC constructs executable MAS specifications of high predictive accuracy without compromising reasoning efficiency.