3 papers
cs.LG2026
Do We Need Frontier Models to Verify Mathematical Proofs?
Aaditya Naik, Guruprerana Shabadi, Rajeev Alur +1
Advances in training, post-training, and inference-time methods have enabled frontier reasoning models to win gold medals in math competitions and settle challenging open problems.…
cs.LO2025
Optimization Modulo Integer Linear-Exponential Programs
S Hitarth, Alessio Mansutti, Guruprerana Shabadi
This paper presents the first study of the complexity of the optimization problem for integer linear-exponential programs which extend classical integer linear programs with the ex…
cs.LG2025
Risk-Sensitive Agent Compositions
Guruprerana Shabadi, Rajeev Alur
From software development to robot control, modern agentic systems decompose complex objectives into a sequence of subtasks and choose a set of specialized AI agents to complete th…