arXiv Machine Learning
Jun 25
MINIF2F-DAFNY: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification
arXiv:2512. 10187v3 Announce Type: replace Abstract: LLMs excel at reasoning, but validating their steps remains challenging.
VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving
arXiv:2606. 19399v1 Announce Type: cross Abstract: LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit.
Related stories
arXiv AI
Jun 6
Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
arXiv:2606. 06468v1 Announce Type: new Abstract: We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement.
arXiv AI
Jun 19
PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured Verification
arXiv:2602. 00510v2 Announce Type: replace Abstract: Most LLM code-synthesis benchmarks rely on unit tests as the reward oracle, but PCB schematic design has none: correctness is defined by structured physical constraints over real IC packages and pin-level assignments, per-task golden references are unavailable, and SPICE simulation does not validate schematic-level correctness.
Hugging Face Trending Papers
Jun 8
TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics
LLMs have recently achieved strong results on formal proving benchmarks. However, existing evaluations remain heavily concentrated on competition-style problems and often fail to capture how models behave on longer, more dependency-rich mathematical developments.
arXiv AI
Jun 9
TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics
arXiv:2606. 09450v1 Announce Type: new Abstract: LLMs have recently achieved strong results on formal proving benchmarks.
arXiv AI
Jul 21
Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution
arXiv:2607. 17352v1 Announce Type: new Abstract: Designing effective Lean proof agents is a central challenge in formal mathematical reasoning.
arXiv AI
Jun 2
Formally Solving Answer-Construction Problems in Lean
arXiv:2505. 18492v5 Announce Type: replace Abstract: Mathematical competition problems fall into two broad types: theorem proving, which asks for a proof of a given statement, and answer construction, which requires constructing a property-satifying object with proofs.
arXiv AI
Jun 19
Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning
arXiv:2606. 19808v1 Announce Type: new Abstract: Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes.
arXiv AI
Jun 6
Evaluation of LLMs for Mathematical Formalization in Lean
arXiv:2606. 05632v1 Announce Type: new Abstract: Within the past few years, the ability of Large Language Models (LLMs) to generate formal mathematical proofs has improved drastically.
arXiv AI
Jun 3
LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
arXiv:2606. 03303v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit strong informal mathematical reasoning but struggle to generate mechanically verifiable proofs in formal languages like Lean.
arXiv AI
Jun 12
Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation
arXiv:2606. 12594v1 Announce Type: new Abstract: Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive.
Hugging Face Trending Papers
Jul 6
TREK: Distill to Explore, Reinforce to Refine
Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution modes lie outside the student's on-policy support. We propose TREK (Teacher-Routed Exploration via Forward KL), a simple staged procedure that uses distillation not for imitation but for exploration support expansion.