AIBullisharXiv – CS AI · Jun 197/10
🧠Researchers demonstrate that the Lean proof assistant can provide fine-grained, process-level feedback during reinforcement learning training for theorem proving, beyond simple binary verification signals. By parsing proof attempts into tactic sequences and leveraging Lean's elaboration system, the approach delivers dense, verified credit signals grounded in type theory, showing improvements over outcome-only baselines on benchmarks like MiniF2F and ProofNet.
AINeutralarXiv – CS AI · Jun 97/10
🧠A comprehensive survey examines the evolution of AI systems for mathematical reasoning, from early rule-based solvers to contemporary language models, neuro-symbolic systems, and verified discovery workflows. The research catalogs major benchmarks, identifies critical failure modes like reward hacking and formalization brittleness, and proposes future directions centered on efficiency and usable AI-assisted formalization.
AIBullisharXiv – CS AI · Jun 97/10
🧠Researchers demonstrated that AI-driven formal proof systems can autonomously solve open mathematics problems, resolving 9 Erdős problems and 44 OEIS conjectures at modest computational cost. This breakthrough validates LLMs as practical research tools when combined with formal verification systems like Lean, marking the first large-scale evaluation of this approach on genuinely open problems.
AIBullisharXiv – CS AI · Jun 27/10
🧠Researchers introduce Expected Value Alignment (EVA), a novel reward-modeling technique that enables Large Language Models to provide continuous numerical scores while maintaining human-readable text output for formal mathematics verification in Lean 4. The method bridges a critical gap between discrete generative outputs and continuous value assessment needed for reinforcement learning in theorem proving systems.
AIBullisharXiv – CS AI · Jun 17/10
🧠Researchers propose Feedback Distillation, a novel post-training method for language models that improves reasoning tasks by having models learn from their own feedback at the token level. Applied to Lean4 theorem-proving, the approach outperforms standard GRPO methods in trajectory diversity and scalability while complementing existing reinforcement learning approaches.
AIBullisharXiv – CS AI · Jun 17/10
🧠ProofWala is an open-source multilingual proof engineering framework that enables neural theorem proving across multiple interactive theorem provers like Lean 4 and Rocq through unified infrastructure. The framework demonstrates that cross-lingual training across different proof assistants improves performance on mathematical proof tasks, with significant gains shown in Lean Mathlib and domain-specific applications.
AIBullisharXiv – CS AI · Jun 17/10
🧠Researchers introduce Hermes, an AI agent that combines informal reasoning with formally verified mathematical proofs in Lean, achieving up to 40% accuracy improvements on difficult math benchmarks while reducing computational costs by 80%. The system addresses a fundamental limitation in LLM reasoning by interleaving exploratory problem-solving with rigorous formal verification.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce proof-state snapshotting, a technique that accelerates automated theorem proving in Lean 4 by reusing elaborated proof states across parallel search branches instead of reconstructing them. The method achieves 5.6-50x speedups (averaging 14x) on benchmark problems, addressing a critical bottleneck where per-branch overhead from import loading and elaboration consumed over 99% of computation time.
AIBullisharXiv – CS AI · May 97/10
🧠Researchers have introduced the AI co-mathematician, an interactive workbench that leverages agentic AI to assist mathematicians in solving open-ended research problems. The system achieves state-of-the-art results on hard benchmarks, scoring 48% on FrontierMath Tier 4, and demonstrates practical value by helping researchers solve open problems and identify new research directions.
AIBullisharXiv – CS AI · Mar 97/10
🧠Researchers propose a new method for training large language models (LLMs) that addresses the diversity loss problem in reinforcement learning approaches. Their technique uses the α-divergence family to better balance precision and diversity in reasoning tasks, achieving state-of-the-art performance on theorem-proving benchmarks.
AIBullisharXiv – CS AI · Mar 57/10
🧠Researchers have developed LeanTutor, a proof-of-concept AI system that combines Large Language Models with theorem provers to create a mathematically verified proof tutor. The system features three modules for autoformalization, proof-checking, and natural language feedback, evaluated using PeanoBench, a new dataset of 371 Peano Arithmetic proofs.
AINeutralarXiv – CS AI · Mar 47/104
🧠Researchers have introduced SorryDB, a dynamic benchmark for evaluating AI systems' ability to prove mathematical theorems using the Lean proof assistant. The benchmark draws from 78 real-world formalization projects and addresses limitations of static benchmarks by providing continuously updated tasks that better reflect community needs.
AIBullisharXiv – CS AI · Mar 37/103
🧠Researchers introduce GAR (Generative Adversarial Reinforcement Learning), a new AI training framework that jointly trains problem generators and solvers in an adversarial loop for formal theorem proving. The method shows significant improvements in mathematical proof capabilities, with models achieving 4.20% average relative improvement on benchmark tests.
AINeutralarXiv – CS AI · Feb 277/107
🧠Researchers introduced LeanCat, a benchmark comprising 100 category-theory tasks in Lean to test AI's formal theorem proving capabilities. State-of-the-art models achieved only 12% success rates, revealing significant limitations in abstract mathematical reasoning, while a new retrieval-augmented approach doubled performance to 24%.
AIBullishOpenAI News · Feb 27/105
🧠Researchers have developed a neural theorem prover for Lean that successfully solved challenging high-school mathematics olympiad problems, including those from AMC12, AIME competitions, and two problems adapted from the International Mathematical Olympiad (IMO). This represents a significant advancement in AI's ability to handle formal mathematical reasoning and proof generation.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers have developed a multi-agent AI system in Lean 4 that formalizes asymptotic statistical theory, a mathematically complex domain combining convergence statements, functional analysis, and regularity conditions. The hypothesis-disciplined approach ensures every formalization claim is anchored to source mathematics, producing axiom-clean and human-audited proofs for parametric and semi-parametric statistical models.
AIBullisharXiv – CS AI · Jun 126/10
🧠Pythagoras-Prover introduces a family of efficient Lean theorem provers that achieve state-of-the-art performance with significantly fewer parameters than existing models, using novel training techniques including curriculum learning and augmented data generation. The 4B-parameter model outperforms DeepSeek-Prover-V2-671B by 167x parameter efficiency, while the 32B model sets new benchmarks on formal mathematics tasks.
AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers developed a step-level verification framework that improves Large Language Models' ability to evaluate complex mathematical proofs by maintaining detailed context for each deduction and constraining theorem sources, rather than relying on global evaluation. Testing on research-level proofs revealed that unconstrained approaches fail to catch subtle logical errors, while the new method reveals that remaining verification failures stem from implicit domain conventions rather than hallucinations.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce TheoremBench, a comprehensive Lean4 benchmark for evaluating large language models on formal mathematics theorem proving. Unlike existing competition-focused benchmarks, TheoremBench assesses how LLMs handle longer, dependency-rich mathematical proofs through both standalone theorems and structured families of related subtasks, revealing that current models remain inefficient and biased toward simpler problems.
AINeutralarXiv – CS AI · Jun 56/10
🧠LeanMarathon introduces a multi-agent system that automates the formalization of research mathematics in Lean, solving long-horizon verification challenges through an evolving blueprint architecture. The system successfully formalized seven theorems across recent research papers spanning four Erdős problems without requiring manual verification shortcuts, demonstrating progress toward reliable AI co-mathematics.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers have developed the Abduction Prover, a new automation tool for Isabelle/HOL that enhances proof search capabilities in formal verification. By using abductive reasoning to identify useful conjectures, the tool addresses the significant automation limitations that increase the computational cost of formal verification projects.
AIBullisharXiv – CS AI · May 296/10
🧠Researchers introduce Hilbert-Geo, a neural-symbolic AI framework for solving solid geometry problems by combining formal language representation with theorem-based reasoning. The system achieves 77.3% accuracy on solid geometry tasks, significantly outperforming leading AI models like GPT-4 and Gemini-2.5-pro, demonstrating advances in multimodal geometric reasoning.
🧠 GPT-5🧠 Gemini
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce FormalRewardBench, the first benchmark for evaluating reward models in formal theorem proving using Lean 4. The benchmark reveals that frontier LLMs like Claude Opus outperform specialized theorem provers at evaluating proof quality, suggesting that theorem proving ability does not transfer to proof evaluation tasks.
🧠 Claude🧠 Opus
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce VeriContest, a benchmark of 946 competitive-programming problems designed to evaluate AI models' ability to generate not just functional code but also formal specifications and machine-checkable proofs. Testing ten state-of-the-art models reveals a dramatic capability gap: while the strongest model achieves 92% accuracy on code generation alone, performance plummets to 48% on specifications, 14% on proofs, and just 5% end-to-end, identifying proof generation as the critical bottleneck for verifiable code generation systems.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers present a formal framework for recursive reasoning systems that addresses two critical design challenges: how to represent evolving reasoning states and when to terminate iteration. The paper introduces an epistemic state graph representation and proposes the 'order-gap' metric as a stopping criterion, with theoretical guarantees for when this criterion provides meaningful guidance.
