5 papers
Minimality of Random Moore Automata under Prefix-Dependent Congruences
Matías Carrasco, Sergio Yovine
We study prefix-dependent congruences for random deterministic transition systems with state outputs. In this setting, the admissible continuations used to compare two states may d…
TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
Pepe Alonso, Sergio Yovine, Victor A. Braberman
AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed. Current benchmarks focus almost exclusi…
Congruence-based Learning of Probabilistic Deterministic Finite Automata
Matías Carrasco, Franz Mayr, Sergio Yovine
This work studies the question of learning probabilistic deterministic automata from language models. For this purpose, it focuses on analyzing the relations defined on algebraic s…
Analyzing constrained LLM through PDFA-learning
Matías Carrasco, Franz Mayr, Sergio Yovine +4
We define a congruence that copes with null next-symbol probabilities that arise when the output of a language model is constrained by some means during text generation. We develop…
Towards Efficient Active Learning of PDFA
Franz Mayr, Sergio Yovine, Federico Pan +2
We propose a new active learning algorithm for PDFA based on three main aspects: a congruence over states which takes into account next-symbol probability distributions, a quantiza…