Here's Charlie! Realising the Semantic Web vision of Agents in the age of LLMs
This addresses the problem of ensuring reliability and user trust in AI-driven agents for individuals and organizations on the Web, representing an incremental step toward realizing the Semantic Web vision.
The paper tackles the challenge of building trustworthy semi-autonomous AI agents for online interactions by proposing a system that consults users only when necessary, enabling users to teach agents about trusted sources and preferences to maximize control over data and decisions while maintaining convenience.
This paper presents our research towards a near-term future in which legal entities, such as individuals and organisations can entrust semi-autonomous AI-driven agents to carry out online interactions on their behalf. The author's research concerns the development of semi-autonomous Web agents, which consult users if and only if the system does not have sufficient context or confidence to proceed working autonomously. This creates a user-agent dialogue that allows the user to teach the agent about the information sources they trust, their data-sharing preferences, and their decision-making preferences. Ultimately, this enables the user to maximise control over their data and decisions while retaining the convenience of using agents, including those driven by LLMs. In view of developing near-term solutions, the research seeks to answer the question: "How do we build a trustworthy and reliable network of semi-autonomous agents which represent individuals and organisations on the Web?". After identifying key requirements, the paper presents a demo for a sample use case of a generic personal assistant. This is implemented using (Notation3) rules to enforce safety guarantees around belief, data sharing and data usage and LLMs to allow natural language interaction with users and serendipitous dialogues between software agents.