Zhiyang Xun, Daniel D. Johnson, Sarah Schwettmann, Neil Chowdhury
原文摘要
Rare language model behaviors can be difficult to study because obtaining them through ordinary sampling can require a very large number of samples. This motivates the behavior posterior sampling problem: given a language model and a behavior of interest, is there an algorithm that efficiently samples from the model's distribution over transcripts that exhibit this behavior? We introduce PosteriorBench, a benchmark for comparing algorithms by their compute cost and by how close their samples are to the true posterior in forward and reverse KL divergence. PosteriorBench contains 21 tasks on Qwen3.5-0.8B with behavior probabilities from $10^{-5}$ to $10^{-1}$, each with exact posterior samples from a corpus of one billion labeled responses. We find that no method we evaluate is both efficient and faithful: simple methods like prompting are cheap but plateau at a high KL divergence from the posterior, fine-tuning on posterior samples is often cost-prohibitive, and several training methods from prior work do not perform better. Building a posterior sampler that can cheaply approximate the true posterior remains an open problem, and we hope PosteriorBench can measure progress towards this objective. Code and data are available at https://github.com/TransluceAI/PosteriorBench.
Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu 等 12 位作者
原文摘要
We introduce MLE-bench, a benchmark for measuring how well AI agents perform at machine learning engineering. To this end, we curate 75 ML engineering-related competitions from Kaggle, creating a diverse set of challenging tasks that test real-world ML engineering skills such as training models, preparing datasets, and running experiments. We establish human baselines for each competition using Kaggle's publicly available leaderboards. We use open-source agent scaffolds to evaluate several frontier language models on our benchmark, finding that the best-performing setup--OpenAI's o1-preview with AIDE scaffolding--achieves at least the level of a Kaggle bronze medal in 16.9% of competitions. In addition to our main results, we investigate various forms of resource scaling for AI agents and the impact of contamination from pre-training. We open-source our benchmark code (github.com/openai/mle-bench/) to facilitate future research in understanding the ML engineering capabilities of AI agents.