As You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture

2026-06-16

AI Summary

This work addresses the challenge of ambiguous natural language instructions leading to deviations from user intent in agricultural robot task planning. The authors propose a novel architecture that integrates large language models (LLMs) with formal verification: two off-the-shelf LLMs are employed—one to generate task specifications and another to verify their correctness—while linear temporal logic (LTL) underpins a multi-layer feedback loop to ensure alignment with the user’s true requirements. This approach uniquely combines LTL-based verification with a dual-LLM collaborative mechanism, effectively mitigating both linguistic ambiguity and model bias. Experimental results demonstrate that the system substantially enhances the accuracy and reliability of task planning while overcoming the limitations of directly using LLMs to generate LTL formulas.

Abstract

Though robotic systems are now being commercialized and deployed in various industries, many of these systems are highly specialized and often require an advanced skill set to operate and ensure they perform as instructed. To mitigate this problem, we recently introduced a mission planner leveraging LLMs to synthesize mission plans in precision agriculture based on mission descriptions provided in natural language. While the system demonstrates impressive performance, it also suffers from the inherent ambiguities of natural language. In this paper, we extend our system to address this issue by introducing multiple feedback loops in the planning architecture that leverage linear temporal logic (LTL) to ensure the mission planning system meets the specifications formulated by the user while still using natural language. To mitigate potential bias, this is achieved by using two different commercial LLMs in charge of the specification and verification subtasks. Through extensive experiments, we highlight the strengths and limitations of integrating mission verification into a fully autonomous pipeline, particularly regarding an LLM's ability to generate valuable LTL formulas, and show how our proposed implementation addresses and solves these challenges.

Problem

• natural language ambiguity
• mission planning
• formal verification
• precision agriculture
• specification

Innovation

• LLM-based mission planning
• formal verification
• linear temporal logic (LTL)
• natural language to specification
• precision agriculture