AI Paper Atlas

Research map / Large language models / Agents, code and math

miniF2F-Dafny: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification

Mantas Baksys, Stefan Zetzsche, Olivier Bouissou, Sean B. Holden

ICML 2026 · Large language models › Agents, code and math · approach: Formal verification and proof data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LLM-generated proof hints (Claude Opus 4.6, pass@4) to Dafny automationDafny Verifier · miniF2F-Dafny testsolved (%): 38.9 -> 62.7Improved
add LLM-generated proof hints (Claude Sonnet 4.5)Dafny Verifier · miniF2F-Dafny testsolved (%): 38.9 -> 55.7Improved
add LLM hints from Qwen 3 / GPT-OSS modelsDafny Verifier · miniF2F-Dafny testpass@4 (%): 38.9 -> 43.4 (GPT-OSS 20B)Mixed
increase attempts from pass@1 to pass@4 with error correctionClaude Opus 4.6 · miniF2F-Dafny testsolved (%): 58.2 -> 62.7Improved
increase attempts from pass@1 to pass@4 with error correctionClaude Haiku 4.5 · miniF2F-Dafny testsolved (%): 42.2 -> 43.9Improved
use Dafny automation instead of Lean grindempty-proof baseline · miniF2F testsolved (%): 32.4 -> 38.9Improved
use Claude family instead of Qwen/GPT-OSS modelsLLM proof hint generator · miniF2F-Dafny testpass@4 (%): 43.4 -> 62.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy