AI Paper Atlas

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

Let's Explore Step by Step: Generating Provable Formal Statements with Deductive Exploration

Qi Liu, Kangjie Bao, Yue Yang, Xinhao Zheng, Renqiu Xia, Qinxiang Cao, Junchi Yan

ICLR 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation

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 DExploration step-by-step exploration (vs one-shot Conjecturer-Prover) (ablation)Goedel-Prover-V2-8B agent · Lean 4 statement synthesissuccess rate (%): 23.28 -> 54.52Improved
add DExploration step-by-step exploration (ablation)Goedel-Prover-V2-8B agent · Lean 4 statement synthesisproven rate (%): 31.78 -> 64.18Improved
add DExploration step-by-step exploration (ablation)Goedel-Prover-V2-8B agent · Lean 4 statement synthesiscontradictory rate (%): 36.34 -> 9.94Improved
add DExploration step-by-step exploration (ablation)Goedel-Prover-V2-8B agent · Lean 4 statement synthesistoken cost per valid statement: 187K -> 8.8KImproved
add DExploration step-by-step exploration (ablation)Goedel-Prover-V2-8B agent · Lean 4 statement synthesisvalid statements: 1164 -> 2726Improved
add interleaved introducing and deducing from exploratory transformation (vs staged) (ablation)DExplorer · Lean 4 statement synthesisproven rate (%): 52.10 -> 64.18Improved
add interleaved introducing and deducing (vs staged) (ablation)DExplorer · Lean 4 statement synthesisvalid statements: 2340 -> 2726Improved
add interleaved introducing and deducing (vs staged) (ablation)DExplorer · Lean 4 statement synthesistop-500 complexity: 1193 -> 1374Improved
add interleaved introducing and deducing (vs staged) (ablation)DExplorer · Lean 4 statement synthesisoverall complexity: 470 -> 515Improved
add interleaved introducing and deducing (vs staged) (ablation)DExplorer · Lean 4 statement synthesistop-500 item difficulty (lower=harder): 0.09 -> 0.05Improved
add interleaved introducing and deducing (vs staged) (ablation)DExplorer · Lean 4 statement synthesistoken cost per valid statement: 8800 -> 8841No clear effect
add DExploration (vs Conjecturer-Prover, same data and model) (ablation)Goedel-Prover-V2-8B agent · Lean 4 statement synthesisRouge-L (lower=more diverse): 0.174 -> 0.173No clear effect

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