AgentSSL: Can MLE Agents Leverage Unlabeled Data?
cs.AI, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-12
Project page: https://codiscovery.ai/AgentSSL
Terminology
Sources
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- AIRA_2: Overcoming Bottlenecks in AI Research Agents
- Deep Learning Scaling is Predictable, Empirically
- Scaling Laws for Neural Language Models
- Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density
- AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
- Revisiting semi-supervised learning in the era of foundation models
- An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents