Skip to content

LLMs for Executable Multi-Agent System Specification Generation

Sep 2026 · arXiv.org · Vol abs/2609.34619 · 0 citations · 73 references
Computer Science

TL;DR

The proposed `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, is presented.

Abstract

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.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

AgentSpy: Making AI Agent Behavior Observable

AI agents built on large language models (LLMs) run shell commands, read and write files, and reach the network, typically with their user's privileges. However, what an agent does during an execution is difficult to understand: tests assert on the result, and the agent's trajectory records only what the agent reports...

C. Bühler, Matteo Biagiola, Luca Di Grazia et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications

AI agents based on foundation models (FMs) have demonstrated strong capabilities to perform complex open-ended tasks. However, they face some common challenges in practice: (a) agent behavior can deviate drastically even for semantically similar tasks, leading to catastrophically propagated errors; (b) high cost and la...

Peng Qi, Chunliang Lyu, Gang Li et al. · 0 citations
Preprint Oct 2026

Verse: Semantics and Verification of Hybrid Multi-Agent Scenarios

Verifying cyber-physical systems with many interacting agents remains difficult because interactions are mediated by sensors, individual decisions are constrained by environment (map) structure, and the resulting mode space scales combinatorially. We present Verse, a framework for writing agents, maps, and sensors in a...

Yang-Ge Li, Katherine Braught, Alex Yuan et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Capability-Grounded Agentic Planning

Capability-Grounded Agentic Planning (CGAP) is presented, which compiles the tool catalog deterministically into a PDDL model, uses an LLM to turn the request into goals, and solves the model with a classical planner.

Shikha Shrestha, William Yeoh, Ning Zhang et al. · 0 citations

Symbolic Temporal Supervision of LLM Agents Using Contracts

ContrAgent is presented, a contract-based framework for symbolic temporal supervision of LLM agents that matches state-of-the-art LLM-judge and rule-based guardrail baselines while producing deterministic, reproducible verdicts and, in the online mode, orders-of-magnitude lower per-call latency.

Yi-Feng Xiao, Pierluigi Nuzzo · 2 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.