20 results for “Mathematics”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper extends the Hazel Prover interface to support exploratory mathematics for both students and experts.
The paper explores the relationship between AI systems, proof assistants, and the generation of formal mathematics.
Alan Li, Rahul Saha, Anton Xue, Swarat Chaudhuri +3 more
AI was used to improve bounds on the Grothendieck constant $K_G$ in mathematics research, leading to novel insights.
Ahmad Rammal, Niket Patel, Fabian Gloeckle, Amaury Hayat +4 more
The paper introduces AutoformBot, a multi-agent system that successfully autoformalizes a large corpus of open-access graduate-level mathematics textbooks into a verified library in Lean 4, demonstrat…
Simon Kurgan, Evan Wang, Eric Leonen, Sophie Szeto +5 more
The paper introduces TheoremGraph, a unified statement-level dependency graph spanning both informal and formal mathematics.
Michal Garlik, Svyatoslav Gryaznov, Jiaqi Lu, Rahul Santhanam +1 more
The paper studies the meta-mathematics of algebraic circuit lower bounds and their relationship with proof systems and bounded arithmetic theories.
The paper introduces Iteris, an agentic research system, demonstrating its capability to generate numerical evidence, constructions, and proof drafts for open problems in computational mathematics, re…
The paper proposes a multimodal data analytics framework combining knowledge graphs and temporal modeling to accurately predict advanced mathematics learning difficulties and provide early academic wa…
This paper reports on the Composition event series, covering its structure, artist selection process, outreach efforts, and community response.
Xiyu Zhai, Xinyi Chen, Yiping Wang, Runlong Zhou +2 more
A dependent-type-based prover is designed to assist LLMs and humans in writing mathematics, complementing existing systems like Lean and Rocq.
This paper proposes a Genetic Algorithm with constraint repair mechanism for optimally allocating educational resources to high school mathematics students under study time constraints.
The paper investigates automatic detection of hidden misconceptions in student responses and proposes a new assessment rubric and pipeline to address them.
Bowen Wei, Nan Wang, Yuqing Zhou, Jinhao Pan +1 more
The paper proposes COSE, a method that uses an LLM's intrinsic confidence as an uncertainty signal to improve self-evolutionary training, achieving state-of-the-art performance on general reasoning an…
This paper introduces a novel distance metric for Boolean hypercubes, enabling perfect sphere packing in any dimension.
The paper proposes using an LLM aggregator that analyzes complete reasoning traces, demonstrating that trace-level synthesis is superior to traditional consensus methods like majority voting for solvi…
This paper develops distributive laws for parallel composition in a rely/guarantee style theory for reasoning about concurrent programs.
This paper introduces a new distillation reward, the delta signal, for on-policy distillation in reinforcement learning, which captures changes induced by reasoning tuning and improves performance.
The paper introduces an Integrated, cross-Architecture Reasoning (IAR) framework to provide a unified and robust method for interpreting the opaque reasoning processes within Large Language Models.
This paper evaluates the performance of large language models on quiz-style questions covering common and niche topics in six European languages, finding significant knowledge gaps and language-depend…
Justin Asher, Yichuan Cao, Ruichen Qiu, Pietro Pellegrino +1 more
The paper presents Numina Fuse, an agent-native application for formalizing mathematics in Lean 4, and its development and use in formalizing the three-dimensional Kakeya conjecture.