Scaling Lean Theorem Proving for Real-World Code Verification
READ THE ORIGINAL SOURCEOpen original sourcehuggingface.co · Opens in a new tabThe paper presents EasyProver, a Lean proving system using recursive agents, asynchronous search, and parallel tactic probing. With an off-the-shelf frontier model and no extra training, it proves 669/672 PutnamBench problems and all six IMO 2026 formalizations, and resolves 597/600 NTP4VC conditions and all 189 VERINA tasks. The authors also introduce Aegis, which turns competitive programming problems into Rust-Lean verification tasks. Aegis yields 2,045 Rust-Lean program pairs and 11,533 candidate specifications. EasyProver proves 1,054 (52.7%) of a 2,000-statement sample within 30 minutes per statement.
One primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face Daily Papers
- Discovery linkHugging Face
- Linked in sourceView arXiv page
- Linked in sourceView PDF
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Open full article view →- Original paper+45
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
The paper presents EasyProver, a Lean proving system using recursive agents, asynchronous search, and parallel tactic probing. With an off-the-shelf frontier model and no extra training, it proves 669/672 PutnamBench problems and all six IMO 2026 formalizations, and resolves 597/600 NTP4VC conditions and all 189 VERINA tasks. The authors also introduce Aegis, which turns competitive programming problems into Rust-Lean verification tasks. Aegis yields 2,045 Rust-Lean program pairs and 11,533 candidate specifications. EasyProver proves 1,054 (52.7%) of a 2,000-statement sample within 30 minutes per statement.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: huggingface.co. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; results rely on a single unnamed frontier model and the 30-minute per-statement budget.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- EasyProver proves 669 of 672 PutnamBench problems and all six IMO 2026 formalizations without additional training.
- Aegis produces 2,045 differentially validated Rust-Lean program pairs and 11,533 candidate specifications.
- On a stratified 2,000-statement sample from Aegis, EasyProver proves 1,054 (52.7%) within 30 minutes per statement.
Source claims not independently checked; results rely on a single unnamed frontier model and the 30-minute per-statement budget.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
The authors argue existing benchmarks are near saturation, so Aegis offers harder, implementation-level verification tasks over Rust code. The tasks are also proposed for benchmarking other provers and as reinforcement learning rewards.
Limits and open questions
Source claims not independently checked; results rely on a single unnamed frontier model and the 30-minute per-statement budget.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.