AxDafny achieves 92.7% verification success on DafnyBench (6.5 points above prior proof-hint baselines) via verifier-guided repair and introduces the LCB-Pro-Dafny benchmark of 250 problems.
A Minimal Agent for Automated Theorem Proving
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements the core features shared among state-of-the-art systems: iterative proof refinement, library search and context management. We evaluate this agentic approach using qualitatively different benchmarks and compare various frontier language models and design choices. Our results show competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture and a fraction of their cost. Additionally, we demonstrate consistent advantages of an iterative approach over multiple single-shot generations, especially in terms of sample efficiency and cost effectiveness. The implementation is released open-source as a candidate reference for future research and as an accessible prover for the community.
fields
cs.AI 2years
2026 2representative citing papers
Agentic LLM framework autoformalizes 32 Putnam problems and main theorems plus proofs from five STOC papers into Lean 4, with two proofs using only kernel axioms.
citing papers explorer
-
AxDafny: Agentic Verified Code Generation in Dafny
AxDafny achieves 92.7% verification success on DafnyBench (6.5 points above prior proof-hint baselines) via verifier-guided repair and introduces the LCB-Pro-Dafny benchmark of 250 problems.
-
Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
Agentic LLM framework autoformalizes 32 Putnam problems and main theorems plus proofs from five STOC papers into Lean 4, with two proofs using only kernel axioms.