AgentODRL: A Large Language Model-based Multi-agent System for ODRL Generation
Wanle Zhong, Keman Huang, Xiaoyong Du
TL;DR
This paper tackles the challenge of translating complex natural-language data rights policies into ODRL, a task hindered by structural complexity and limited NL-ODRL data. It introduces AgentODRL, a multi-agent system with an Orchestrator-Workers architecture that decomposes tasks into specialized Rewriter, Splitter, and Generator agents, and augments generation with a LoRA-based semantic reflection and a SHACL-based validator loop. A 770-case data-space benchmark underpins the evaluation, showing state-of-the-art grammar and semantic fidelity, with the Orchestrator-Workers workflow delivering near-ceiling performance while reducing token costs. The work demonstrates that architectural decomposition and targeted fidelity strategies can significantly improve NL-to-ODRL automation, offering practical value for scalable data rights management in distributed data spaces.
Abstract
The Open Digital Rights Language (ODRL) is a pivotal standard for automating data rights management. However, the inherent logical complexity of authorization policies, combined with the scarcity of high-quality "Natural Language-to-ODRL" training datasets, impedes the ability of current methods to efficiently and accurately translate complex rules from natural language into the ODRL format. To address this challenge, this research leverages the potent comprehension and generation capabilities of Large Language Models (LLMs) to achieve both automation and high fidelity in this translation process. We introduce AgentODRL, a multi-agent system based on an Orchestrator-Workers architecture. The architecture consists of specialized Workers, including a Generator for ODRL policy creation, a Decomposer for breaking down complex use cases, and a Rewriter for simplifying nested logical relationships. The Orchestrator agent dynamically coordinates these Workers, assembling an optimal pathway based on the complexity of the input use case. Specifically, we enhance the ODRL Generator by incorporating a validator-based syntax strategy and a semantic reflection mechanism powered by a LoRA-finetuned model, significantly elevating the quality of the generated policies. Extensive experiments were conducted on a newly constructed dataset comprising 770 use cases of varying complexity, all situated within the context of data spaces. The results, evaluated using ODRL syntax and semantic scores, demonstrate that our proposed Orchestrator-Workers system, enhanced with these strategies, achieves superior performance on the ODRL generation task.