Live intelligence

Latest AI updates

1 updates
Research

AgentSSL: Can MLE Agents Leverage Unlabeled Data?

This paper introduces Agentic Semi-Supervised Learning (AgentSSL), which frames semi-supervised learning as a program search problem and tests MLE agents under scarce labeled data and abundant unlabeled data. The agents synthesize code combining established SSL techniques and outperform strong human-engineered baselines in 8 of 12 settings by up to +21.8%. The authors identify program selection as a critical bottleneck and release ProgramSelectBench, a benchmark with 16,977 agent-generated and human-engineered SSL programs. They also evaluate AgentSSL on real-world ecology detection tasks to explore transfer beyond controlled benchmarks.

AgentSSLProgramSelectBenchsemi-supervised learning