arXiv AI
Reset Early, Reset Often, Eliminate Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 1
Modal CEGAR-tableaux with RECAR and resolution-based SAT-shortcuts
arXiv:2606. 31878v1 Announce Type: cross Abstract: We investigate two approaches for extending CEGAR-tableaux with SAT-shortcuts using a previously known approach called RECAR but also a totally new approach using the modal resolution theorem prover KSP as an oracle.
arXiv AI
Jul 21
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
arXiv:2509. 00930v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general reasoning, yet the community lacks controllable, scalable, and verifiable tools to analyze and improve these abilities.
arXiv AI
Jul 2
LRAT-Catcher: Importing SAT Solver Certificates into Lean4 by Reflection
arXiv:2607. 00815v1 Announce Type: cross Abstract: SAT solvers settle combinatorial problems beyond the reach of interactive theorem provers and produce LRAT certificates for independent verification.
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.
arXiv AI
Oct 31
Verifiable LLM-Guided Focal SMT Solving for Quantified Arrays
The paper introduces LinguaArray, a framework that uses large language models (LLMs) to suggest a small set of focal ground terms or constraints—called a Semantic Focus Set—in quantified array SMT solving. The LLM’s suggestions are then verified by a conventional SMT solver, which remains the sole source of proof. Experiments on 1,015 SMT-LIB instances show that LinguaArray solves up to 69.1% of cases and increases the number of solved instances by 105%–397% compared to the backends alone.
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.