arxiv:2609.24555
Muhan Zhang
Muhansp
AI & ML interests
Mathematical reasoning, LLM evaluation & benchmarks, multi-agent systems, test-time reasoning, AI agents
Recent Activity
submitted a paper 2 days ago
The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence authored a paper 10 days ago
The Endless Exam: Mathematical Constructions from Today's Models toward SuperintelligenceOrganizations
None yet