The University of Napoli, often referred to as the University of Naples Federico II, was established in 1224 and is one of the world’s oldest universities, founded by a head of state. It is a major public research university in Naples, Italy, with three semi-independent divisions and multiple campuses, known for its influential alums and international collaborations. In collaboration with Parthenope University, NECLA researchers focused on leveraging multimodal data—encompassing both vision and language—for learning from unlabeled sources. Our joint efforts contributed to improved data efficiency and robustness in AI systems, particularly for complex tasks such as image captioning and cross-modal retrieval.

Posts

XPF: Agentic AI System for Business Workflow Automation

/in /by

In this paper, we propose a novel agentic AI system called XPF, which enables users to create “agents” using just natural language, where each agent is capable of executing complex, real-world business workflows in an accurate and reliable manner. XPF provides an interface to develop and iterate over the agent creation process and then deploy the agent in production when satisfactory results are produced consistently. The key components of XPF include: (a) planner, which leverages LLM to generate a step-by-step plan, which can further be edited by a human (b) compiler, which leverages LLM to compile the plan into a flow graph (c) executor, which handles distributed execution of the flow graph (using LLM, tools, RAG, etc.) on an underlying cluster and (d) verifier, which helps in verification of the output (through human generated tests or auto-generated tests using LLM). We develop five different agents using XPF and conduct experiments to evaluate one particular aspect i.e. difference in accuracy and reliability of the five agents with “human-generated” vs “auto-generated” plans. Our experiments show that we can get much more accurate and reliable response for a business workflow when step-by-step instructions (in natural language) are given by a human familiar with the workflow, rather than letting the LLM figure out the execution plan steps. In particular, we observe that “human-generated” plan almost always gives 100% accuracy whereas “auto-generated” plan almost never gives 100% accuracy. In terms of reliability, we observe through Rouge-L, Blue and Meteor scores, that the output from “human-generated” plan is much more reliable than “auto-generated” plan.

Read more