Automated Theorem Proving
Overview
Automated theorem proving studies how to turn goals and assumptions into proofs that trusted checkers can validate, supporting dependable mathematics and software verification. Approaches range from symbolic search, resolution, tableaux, SAT/SMT solving, and tactics to language models that retrieve lemmas, decompose goals, learn from proof traces, and use Lean, Rocq, Isabelle, or Dafny feedback. Evaluation spans contest benchmarks such as miniF2F and PutnamBench, large proof libraries, code-verification tasks, and research-level problems. A central challenge is moving from benchmark success to robust, economical proofs whose formal statements faithfully capture the intended mathematics or specifications; autoformalization and semantic verification remain difficult.
Latest papers
174 papers18 papers in the last four weeks, down 36% on the four weeks before. 0.1% of all new papers.