LLMs for Executable Multi-Agent System Specification Generation
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
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.
Key facts. No citing papers in the map yet (data through 7 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.
Builds on
18 of 73 references.
Closest ancestors · 1
Same direction, newest first
Other references · 17
- 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 496
- 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
- 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
- 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
- 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 204
- 2024Chain of Thoughtlessness? An Analysis of CoT in Planningcited by 100
- 2023Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Textcited by 59
- 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
- 2025LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actionscited by 10
- 2017Expressive Stream Reasoning with Lasercited by 7
- 2024ChatLogic: Integrating Logic Programming with Large Language Models for Multi-Step Reasoningcited by 7
- 2019Composite Event Recognition for Maritime Monitoringcited by 4
5 more
- 2019A Distributed Approach to LARS Stream Reasoning (System paper)cited by 4
- 2021Combining Event Calculus and Description Logic Reasoning via Logic Programmingcited by 4
- 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programmingcited by 4
- 2017Ticker: A System for Incremental ASP-based Stream Reasoningcited by 3
- 2021CORE: a Complex Event Recognition Enginecited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
- 2025Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications
- 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
- 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
- 2024Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
- 2025MinionsLLM: a Task-adaptive Framework For The Training and Control of Multi-Agent Systems Through Natural Language
- 2026Provable Coordination for LLM Agents via Message Sequence Charts
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges