8 papers
SmartEval: A Benchmark for Evaluating LLM-Generated Smart Contracts from Natural Language Specifications
Abhinav Goel, Agostino Capponi, Alfio Gliozzo +1
We introduce SmartEval, a benchmark for systematically evaluating the quality of Solidity smart contracts generated by large language models (LLMs) from natural language specificat…
Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows
Alfio Massimiliano Gliozzo, Junkyu Lee, Nahuel Defosse
Agentic AI is rapidly transitioning from research prototypes to enterprise deployments, where requirements extend to meet the software quality attributes of reliability, scalabilit…
An end-to-end agentic pipeline for smart contract translation and quality evaluation
Abhinav Goel, Chaitya Shah, Agostino Capponi +1
We present an end-to-end framework for systematic evaluation of LLM-generated smart contracts from natural-language specifications. The system parses contractual text into structur…
Transduction is All You Need for Structured Data Workflows
Alfio Gliozzo, Naweed Khan, Christodoulos Constantinides +4
This paper introduces Agentics, a functional agentic AI framework for building LLM-based structured data workflow pipelines. Designed for both research and practical applications,…
Agentic AI for Clustering, Relationship Discovery, and Semantic Trading in Prediction Markets
Agostino Capponi, Alfio Gliozzo, Brian Zhu
Prediction markets allow users to trade on outcomes of real-world events, but are prone to fragmentation with overlapping questions, implicit equivalences, and hidden contradiction…
DAO-AI: Evaluating Collective Decision-Making through Agentic AI in Decentralized Governance
Agostino Capponi, Alfio Gliozzo, Chunghyun Han +1
This paper presents a first empirical study of agentic AI as autonomous decision-makers in decentralized governance. Using more than 3K proposals from major protocols, we build an…