Publications (8)
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
Yu Feng, Nathaniel Weir, Kaj Bostrom +5
LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasonin…
ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Models
Andre He, Nathaniel Weir, Kaj Bostrom +4
Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising approach for training reasoning language models (RLMs) by leveraging supervision from verifiers. Al…
A Neurosymbolic Approach to Natural Language Formalization and Verification
Chenyang An, Sam Bayless, Stefano Buliani +27
The paper presents ARc, a system that combines large language models with automated reasoning to formally translate natural‑language policies and verify their logical correctness,…
SAT Modulo Monotonic Theories
Sam Bayless, Noah Bayless, Holger H. Hoos +1
We define the concept of a monotonic theory and show how to build efficient SMT (SAT Modulo Theory) solvers, including effective theory propagation and clause learning, for such th…
DRAT Proofs of Unsatisfiability for SAT Modulo Monotonic Theories
Nick Feng, Alan J. Hu, Sam Bayless +5
Generating proofs of unsatisfiability is a valuable capability of most SAT solvers, and is an active area of research for SMT solvers. This paper introduces the first method to eff…
The Configurable SAT Solver Challenge (CSSC)
Frank Hutter, Marius Lindauer, Adrian Balint +3
It is well known that different solution strategies work well for different types of instances of hard combinatorial problems. As a consequence, most solvers for the propositional…