Search papers, labs, and topics across Lattice.
This paper introduces an autonomous agent capable of designing machine learning algorithms for wireless resource management, specifically targeting cell-edge power control in multicell networks. By utilizing an autoresearch protocol, the agent autonomously edits training scripts and evaluates changes based on a single immutable performance metric, achieving remarkable efficiency and effectiveness. The agent's approach resulted in a 99.5% convergence to a reference solution with a 600x reduction in inference cost, demonstrating its ability to recover optimal structures rather than merely tuning parameters.
An autonomous AI agent achieved 99.5% of the optimal solution for cell-edge power control while slashing inference costs by 600x, revolutionizing the role of researchers in algorithm design.
Designing machine learning algorithms for wireless resource management is labour-intensive: the architecture, the loss function and the training recipe are all specified by hand. We demonstrate that this design layer can be surrendered to an autonomous agent in its entirety. We adopt the autoresearch protocol, in which an AI coding agent edits a training script, runs a fixed-budget experiment, and retains or discards the change according to a single immutable metric. We grant the agent authority over the architecture family, the input representation, the output parameterization, the loss function and the task-sampling law, and set it a target chosen for its difficulty: sum-least-percentile-rate power control across a multicell network. The formulation targets cell-edge throughput and is non-convex, non-smooth and strongly NP-hard away from its max-min vertex. Safeguards render the results trustworthy: a hash-pinned evaluator, an enforced inference contract and a pre-registered falsifier per experiment. In eighty-one unattended experiments over twenty-six hours, the agent reached $99.5\%$ of a converged minorization-maximization reference in one fixed-cost inference pass, at roughly $600\times$ lower inference cost, closing $94\%$ of the gap from its first working architecture, with one parameter set serving every network size and percentile target. It recovered provable structure rather than tuned constants: the output parameterization it discovered reproduces the exact max-min-optimal allocation at the minimum percentile, for every value of the trained weights.
