Code and data for the paper. This is an empirical study of when multi-agent LLM interaction helps and when it hurts on scientific optimization tasks. Different model families approach open problems ...
Across 157 enterprises, organizations are granting AI agents more autonomy while trusting the evaluations meant to gate that ...
A multi-algorithm solver for a real-world combinatorial optimization problem that fuses Traveling Salesperson (TSP), 0/1 Knapsack, and the Generalized Assignment Problem (GAP) into a single ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results