Direct Optimization of Generators for Search in Automated Theorem Proving

arXiv:2603.19715v1 Announce Type: new Abstract: Formal verification via interactive theorem proving is increasingly used to ensure the correctness of critical systems, yet

arXiv:2605.01327v1 Announce Type: new Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of

arXiv:2606.20068v1 Announce Type: new Abstract: While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic

arXiv:2603.27195v1 Announce Type: new Abstract: Designing microstructures that satisfy coupled cross-physics objectives is a fundamental challenge in material science. This

arXiv:2603.19828v1 Announce Type: new Abstract: Autoformalization aims to translate natural-language mathematics into compilable, machine-checkable statements. However, semantic

arXiv:2603.18388v1 Announce Type: new Abstract: Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt

arXiv:2605.20244v1 Announce Type: cross Abstract: We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and

arXiv:2604.15839v1 Announce Type: new Abstract: Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that