AI Paper Atlas

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

ProofOptimizer: Training Language Models to Simplify Proofs without Human Demonstrations

Alex Gu, Bartosz Piotrowski, Fabian Gloeckle, Kaiyu Yang, Aram H. Markosyan

ICLR 2026 · Large language models › Agents, code and math · approach: Retrieval-augmented formal theorem proving · 12 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 RL training after expert iteration (ablation)ProofOptimizer · miniF2Fred@1 (%): 49.0% -> 63.6%Improved
add RL training after expert iteration (ablation)ProofOptimizer · miniF2Fred@32 (%): 72.3% -> 70.9%Hurt
add RL training after expert iteration (ablation)ProofOptimizer · PutnamBenchred@32 (%): 26.3% -> 21.1%Hurt
add test-time RL (ablation)ProofOptimizer-RL (It 2) · PutnamBenchred@1 (%): 14.9% -> 23.8%Improved
more expert iteration rounds (ablation)ProofOptimizer-ExpIt · miniF2Fred@32 (%): 67.0% -> 72.3%Improved
fine-tune 7B model for proof simplification vs Gemini-2.5-ProQwen2.5-7B-Instruct · miniF2Fred@32 (%): 57.2% -> 72.3%Improved
add proof state annotations to Gemini-2.5-Pro prompt (ablation)Gemini-2.5-Pro · miniF2Fred@1 (%): 24.3% -> 26.4%No clear effect
repair failed simplifications with execution feedback instead of resampling (ablation)ProofOptimizer-ExpIt · miniF2F, PutnamBenchproof length: repaired length 644 -> 576 after linter (still longer than originals often)Hurt
iterative proof shortening with more iterations/samples (ablation)ProofOptimizer-ExpIt · miniF2Favg proof length (tokens): 334 -> 75Improved
SFT on simplified proofs instead of original proofs (ablation)Qwen2.5-7B-Instruct Lean base · miniF2Fpass rate: about +2%Improved
optimize heartbeats instead of proof length (ablation)ProofOptimizer-ExpIt · miniF2Fproofs with >10% speedup: 114/194 -> 138/194 (proofs somewhat longer)Mixed
shorten proofs by lengthProofOptimizer-ExpIt · PutnamBenchexecution time: 50/75 proofs >10% speedupMixed

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