Pedro Orvalho
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1Logic×1
Frequent co-authors
Research Timeline
2026
Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability
The paper proposes a hybrid reasoning framework where Large Language Models (LLMs) generate code to encode complex optimization problems into a preference-based Maximum Satisfiability (MaxSAT) format, which is then solved by an exact solver to achieve verifiable and highly accurate results.
Highlighted terms show continued research focus across papers