learning-augmented algorithms 1offline optimization 1PAC guarantees 1sample complexity 1verifiable certificates 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CY2026
State-dependent error correlations shape voting thresholds in committees of AI agents
Haifeng Li, Mo Hai
The aggregation benefit of a committee of artificial intelligence (AI) agents comes from complementary information across members. Classical voting guarantees assume independent er…
cs.SE2026
Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
Haifeng Li, Mo Hai
Large language models now translate natural-language descriptions of decision problems into solver-ready optimization models, and they fail silently. A generated model often runs a…
cs.LG2026
CASP: Learning-Augmented Offline Approximation with Verifiable Certificates and Bounded-Loss PAC Guarantees
Haifeng Li, Mo Hai
The paper proposes CASP, a learning-augmented framework that uses machine‑learned predictions to prune the search space of offline NP‑hard optimization problems, while a polynomial…