6 papers
Dense Neuro-Symbolic Reasoning in a Unified Geometry State
Ruoran Xu, Wending Gao, Haoyu Cheng +2
Geometry reasoning is naturally stateful: solving a problem repeatedly alternates between structural proposals and exact deductions. We formulate this process as dense neural-symbo…
Symbolic Search Is Not Exhausted: Persistent Proof-Space Exploration in Lean4
Ruoran Xu
Formal theorem proving increasingly combines learned semantic guidance with verified symbolic execution. The quality of the symbolic search substrate therefore determines how much…
PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?
Ruoran Xu, Wending Gao, Liyunfeng Chen +5
Understanding how (multimodal) large language models perform on physics problems requires benchmarks that reflect the difficulty and breadth of expert-level physical reasoning. Exi…
FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation
Ruoran Xu, Wending Gao, Xiaoqing Kang +1
Math reasoning has achieved significant progress with the rapid advancement of Multimodal Large Language Models (MLLMs), however analytic geometry remains largely underexplored, pr…
Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning
Ruoran Xu, Haoyu Cheng, Bin Dong +1
Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of works focus on plane geometry w…
Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
Ruoran Xu, Borong She, Xiaobo Jin +1
Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such…