Mle-Bench Lite

LLM agents have recently shown promise in automating machine learning engineering by editing model and training code under execution feedback. Data, however, remains largely outside this agentic optimisation loop. We frame pre-training data selection as heuristic engineering over per-document features, i.e., lexical statistics, categorical labels, and perplexity. We introduce AutoData, an agent that searches directly over executable selection algorithms. Unlike prior data mixture methods that optimise weights over a fixed set of domains, AutoData searches a richer program space of scoring, stratification, and stochastic selection rules, discovering feature interactions automatically by iteratively refining algorithms with validation feedback from a proxy model. Within an overnight search, AutoData discovers a selection algorithm that outperforms existing human-designed curation pipelines. Despite being searched only on this small proxy, the discovered recipe transfers to larger scales and improves the downstream metric CORE. These results suggest that data engineering can be treated as an agentic machine learning problem, extending autonomous research from model and training-code optimization to the data.

Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteration - the cycles of research, implementation, training, debugging, evaluation, and launch required to surface a single statistically significant improvement. A typical ranking stack contains numerous differentiated models with heterogeneous data, architectures, and infrastructure constraints, and each cycle takes days to weeks of senior engineer attention per model. As a result, techniques that have proven effective on one model diffuse into others slowly and unevenly, leaving substantial recoverable signal unexplored. We present Agentic ML Exploration (A-MLE), an autonomous LLM-agent system that systematically explores ML techniques across a portfolio of ads ranking models. A-MLE decomposes ML iteration into five stages involving hypothesis generation, exploration strategy, experiment execution, result analysis and shared knowledge substrate which are orchestrated by a single agent that invokes domain-specific skills and agentic workflows against a sandboxed execution layer, with human-in-the-loop checkpoints at each stage boundary. We deploy A-MLE across a representative set of large-scale ads ranking models and evaluate it along a tiered capability framework (tool availability, autonomous workflow execution, and open-ended exploration). We further report a controlled cross-LLM study using a fixed agent loop, which surfaces qualitative differences in execution reliability and exploration aggressiveness across the Claude Sonnet, Gemini, and GPT families. We discuss failure modes and the design choices that govern reliability. Our findings suggest that agentic exploration is a practical force multiplier for ML engineers in industrial recommenders, especially for the long tail of models that rarely receive expert attention.

Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys.

Comparisons between AutoML systems at short time budgets -- tens of seconds rather than hours -- are common in tool READMEs and workshop papers, and they are easy to get wrong. We report a case study in which a simple AutoML engine, Orcetra, appeared to beat FLAML and AutoGluon on 513 OpenML datasets, winning 57.1% of them at a nominal 60-second budget and 78.4% of datasets against FLAML alone at 30 seconds. Both margins came from protocol defects that a results table cannot show. The search loop scored every candidate on the test split and reported the best, making the headline metric a maximum over dozens of noisy estimates while the baselines selected on training data and touched the test set once; and the budget was checked before launching a candidate but never enforced during one, so the system consumed a median of 120 s against a 60-second budget, 2.24x the wall-clock AutoGluon used. Re-running with selection moved to a validation split, the deadline enforced externally and every framework pinned to an equal share of the machine, Orcetra's win rate on the re-run subset falls from 59.4% to 34.3% and no pairwise difference against either competitor remains significant. Recording both estimands inside a single search lets us attribute the collapse: the selection rule accounts for 4.8 percentage points and unequal compute for most of the rest. The same traces give the selection bias as a function of budget, measured rather than assumed: it grows with $K$ but reaches only 0.27 accuracy points, about five times below the $σ\sqrt{2\ln K}$ bound a marginal-standard-error argument predicts, because candidates scored on shared test rows cancel most of the noise. We close with a checklist for short-budget comparisons. Code, per-dataset results and the scripts that regenerate every number and figure in the paper are released with it.

Autonomous research agents can generate hypotheses, execute experiments, and draft manuscripts, yet their outputs often contain unsupported claims and inconsistencies between research questions, experiments, results, and conclusions. We argue that this problem is partly architectural: existing systems organize research as sequential pipelines but do not explicitly maintain or validate the evolving claim-evidence structure across stages. In this paper, we introduce EviGraph, an autonomous research framework that represents the research process as a typed evidence graph containing Problem, Gap, Hypothesis, Experiment, Finding, and Claim nodes. The graph serves as the operational state of the agent rather than a post-hoc record. EviGraph inspects evidence chains for missing dependencies, semantic misalignment, and result-claim inconsistencies, localizes the earliest weak node, and regenerates its affected downstream subgraph. Graph checkpointing prevents unsuccessful repairs from corrupting previously validated evidence. Manuscripts are generated only after every retained claim is grounded in a validated evidence chain. Experiments on ARC-Bench-ML and NanoResearch-20 show that EviGraph outperforms the compared end-to-end research-agent baselines in overall research performance, improves Claim Support Rate by 40.19% over the strongest baseline, and achieves 87.73% Experimental Data Consistency. These results demonstrate the value of explicit evidence-state maintenance for reliable autonomous research.

Multiple sclerosis (MS) is diagnosed through clinical assessment, magnetic resonance imaging, laboratory evidence when appropriate, and exclusion of better explanations. Blood RNA expression data may contain disease associated immune signal, but a blood RNA classifier cannot be treated as a replacement for clinical diagnosis. This paper presents MS-MLB (Multiple Sclerosis Machine Learning Benchmark), a reproducible open benchmark for machine learning based MS research classification from whole blood RNA expression data. MS-MLB uses the public GSE17048 cohort, converts it into an MS versus healthy control task, and evaluates multiple algorithms under a shared, leakage controlled pipeline that a researcher can rerun without reconfiguring the evaluation. The evaluation includes nested cross-validation, an untouched stratified holdout set, bootstrap confidence intervals, ROC and precision recall analysis, calibration measurement, and an exploratory MS Research Score. In the final benchmark summary, Gradient Boosting ranked first by MS Research Score on the holdout set, with an MS Research Score of 93.83, AUC-ROC of 0.989, sensitivity of 0.950, specificity of 0.778, $F_{1}$ score of 0.927, and Brier score of 0.050. Prior studies have applied machine learning to MS blood transcriptomic data, including PBMC stage classification and whole blood diagnostic signature modeling. The contribution here is different and narrower. To our knowledge, MS-MLB is the first open benchmark focused on MS versus healthy control classification from GSE17048 whole blood RNA expression data with a documented external model submission pathway built into the framework. The score is intended for research comparison only and has not been clinically validated. The benchmark is accessible here: https://github.com/duckyquang/MS-MLB.

Large language models (LLMs) have demonstrated a strong ability to generate syntactically correct code from natural-language specifications. In this study, we explore how LLMs can be harnessed to automatically translate a neutral graph representation of fluid system models into executable code for two widely adopted simulation environments: the Python library WNTR and the Modelica Standard Library. We conduct a systematic comparison of ten state-of-the-art LLMs and six prompting strategies that differ in the contextual information supplied (e.g., code or documentation). For each configuration we assess the generated code using a suite of software-quality metrics and we validate the functional fidelity of the resulting simulation models by reproducing benchmark fluid system scenarios. Our findings offer concrete guidance for researchers and engineers seeking to integrate LLM-driven code synthesis into model-based design pipelines. While the best-performing configurations achieve acceptable syntactic quality, we observe substantial gaps remain in simulation fidelity.

Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed for studying this capability. We introduce OpenMLE, an open full-stack system for RSI research in MLE, spanning verifiable task environments with execution feedback (OpenMLE-Gym), operator learning (OpenMLE-RL), and long-horizon search (OpenMLE-Evo). On this stack we post-train Frontis-MA1 (35B) as a meta-evolution agent for MLE, aligning post-training and inference around four atomic program-evolution operators (Draft, Improve, Debug, Crossover): the same operators are trained via execution-grounded SFT and RL on data deduplicated against all evaluation benchmarks, then composed into long-horizon search, coupling learning and evolution in a single loop. On MLE-Bench Lite under a 12-hour per-task budget on one RTX 4090 capped at 12 GB VRAM, Frontis-MA1 (35B) improves Medal Average from 39.39% to 60.61% over its base model with OpenMLE-Evo, and reaches 71.21% with OpenMLE-Evo-Max (benchmark-independent experience priors and asynchronous search), exceeding GPT-5.5 + Codex and approaching GPT-5.6 Sol and the 2.8T Kimi K3. On held-out NatureBench Lite, both components transfer: with the framework fixed, swapping in the trained model raises Match-SOTA from 50% to 70%; with the model fixed, swapping in OpenMLE-Evo raises it from 20% to 50%. We release the model weights and the full OpenMLE stack to enable reproducible research on executable AI4AI toward RSI. Code: https://github.com/FrontisAI/OpenRSI

Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and validating training-data strategies, and learning from checkpoint feedback. Can LLM agents automate this loop? Existing benchmarks entangle research decisions with optimization, serving, evaluation, and systems implementation, obscuring agents' research capability. We introduce RSIBench-Data, a controlled benchmark of LLM agents as data-centric researchers with a fixed post-training stack. Agents iteratively revise training-data strategies for a fixed target model; training and serving use Tinker-backed services, official evaluation runs through Harbor and E2B sandboxes, and budgets are fixed across agents. We evaluate four frontier agents on six benchmarks across software engineering, terminal use, scientific question answering, and mathematics. Agents demonstrate core data-centric research capabilities: in 58.33% of settings, they improve upon the first valid attempt by refining strategies from feedback. However, improvement is inconsistent. Among searches continuing after the best observed score, 78.26% end with a lower-scoring final attempt, while the rest only recover the same peak. A strong candidate may therefore appear early or midway through a run even as later revisions fail. Trajectory analysis identifies four patterns in stronger runs: accurate hypotheses, validation-grounded supervision, behavior-aligned data, and preservation of strong checkpoints. These findings suggest that current agents can make useful data-centric discoveries but cannot yet translate feedback into consistent improvements. RSIBench-Data provides a measurable, auditable testbed for the research capabilities required for recursive self-improvement. We open-source our code at https://github.com/evolvent-ai/RSIBench-Data.

Material property prediction (MPP) infers key properties from chemical composition and structure, accelerating the discovery and optimization of novel materials. In the realm of MPP, MatBench is a widely accepted benchmarking tool that defines over ten significant problems and provides the paradigm of performance evaluation for AI prediction models. Even though MatBench works well in benchmarking the performances of prediction models on in-distribution (ID) tasks and datasets, it lacks the ability to reflect their performances on out-of-distribution (OOD) material data, resulting failure in new material discovery. By combining the pipelines of MatBench and the existing researches on OOD performance evaluation, this study enables a huge space of benchmarking configurations, comprehensively reflecting the performances, abilities, and disadvantages of various AI prediction models. This work reports that the discrepancy of performances at different configuration values is huge and can be illustrated with prior knowledge and novel insights, therefore consideration of causal effect of configurations on performance results is necessary. In case of the impossibility of enumerative benchmarking at every configuration, this work further proposes AutoMatBench, an automatic toolkit with Bayesian optimization. Experiments with AutoMatBench reports that, within twelve steps of optimization, the similar results with MatBench and former OOD research can be accessed while more than half of the cost are saved. Besides, this tool also yields more essential findings on MPP benchmarking, positively contributing to the cost and efficiency of new material discovery.

Technical lectures mix Mandarin speech with English technical terms. These terms carry the core meaning of the lecture, yet they occupy few characters. Character error rate (CER) therefore hides their recognition failures. We study whether lecture context helps recognize these terms. We build a term-rich Mandarin AI/ML lecture benchmark, and we define term-centric metrics that measure technical-term recognition directly. We then propose a two-pass, reference-free decoding method. The first pass runs segment-only ASR. We extract the most frequent technical terms from the first-pass hypotheses, and we prompt the recognizer with this self-built glossary in the second pass. Across five ASR backbones, the first-pass glossary raises term recall for every model and holds or lowers CER on all five. On Breeze-ASR-25 it lifts term recall from 52.50% to 60.13% while lowering CER, and a hybrid that adds a small external term list reaches 62.05% recall and 82.73% term precision. Lecture context, recovered from the model's own output, is a practical signal for technical-term recognition. Term-centric evaluation exposes errors that CER misses.

Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the landscape of over one hundred methods remains fragmented. We therefore present OmniOpt, a unified survey and benchmark cookbook of optimizers for the research community. OmniOpt rests on four coupled components. First, we treat every optimizer update as a structured transformation through a five-stage meta-pipeline, and show that most methods engage only one or two of these stages. Second, we use norm-constrained linear minimization oracles (LMOs) to unify different optimizers. Third, these two views ground a dual-dimension taxonomy, one dimension assigning each method to a mechanism family and the other recording the measurable training objectives it aims to improve. Fourth, and at the core of this paper, we instantiate the full taxonomy in a unified cross-domain benchmark spanning representative optimizers, model scales, and training regimes from language model pretraining to image classification, systematically analyzing each method family across multiple effect objectives and laying out their trade-offs. OmniOpt thus supplies the research community with an operational coordinate system for selecting optimizers under explicit mechanism and objective assumptions, and charts a direction for the future development of the optimizer community.

Mutual information (MI) estimation is a central problem in machine learning and statistics; however, existing benchmarks typically evaluate estimators on simplified, low-dimensional distributions, leaving their performance on complex, realistic data largely unexplored. We address this gap with a comprehensive benchmarking framework grounded in a unified copula-theoretic perspective that subsumes existing benchmarks as special cases. Within this framework, we propose two complementary families of tests: a copula-first family that systematically varies ground-truth MI, dimensionality, and marginal complexity using synthetic and flow-based transformations; and a marginals-first family that couples real-world image data with controlled dependency structures, extending the classic same-class-pairing paradigm. We use this suite to extensively evaluate three classes of estimators: non-parametric, discriminative, and generative. Contrary to prevailing assumptions, our results indicate that there is no universal winner: each category can systematically outperform all other estimators under specific setups. By analyzing these cases, we identify fundamental estimation barriers and propose new tests that more effectively stress these specific limitations. We share the open source code at https://github.com/VanessB/mutinfo.

ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchical multi-agent system that organizes cross-competition knowledge into three scope tiers (global, domain, and competition-specific), each coupled to a matching agent level. An orchestrator coordinates domain specialists and promotes learning between tiers via LLM-driven abstraction. A controlled ablation provides evidence for scoped loading: holding a 159-skill inventory constant across 8 competitions, tiered loading achieves a 100% medal rate while flat loading reaches only 62.5%, the same medal rate as loading no skills, and consumes 2x the output tokens. On the full MLE-Bench Lite benchmark (22 Kaggle competitions), HASTE reaches a medal rate of 77.3% using Claude Sonnet 4.6 at 12h per competition; this is a single-seed campaign result, and multi-seed replication is the priority follow-up. In a cold-start run, the system begins with no accumulated skills. In warm-start runs, it reloads skills learned from earlier competitions, using only global and domain-level skills for transfer across competitions. Warm starts use 52% fewer refinement iterations, and the fraction of proposed changes kept by the agent rises from 42% at low inventory to 85% once 50+ skills are available. These results suggest that better knowledge organization can partly substitute for model strength and compute budget in ML-engineering agents.

Low-light image enhancement algorithms (LIEAs) aim to improve the visibility of images captured under poor illumination. However, the enhancement process often introduces artifacts such as noise amplification, color shift, structural damage, and over-exposure, which degrade the perceptual quality of the enhanced images. Therefore, a reliable image quality assessment (IQA) metric for evaluating enhancement effects is of great importance for both the development of LIEAs and their practical applications. In this paper, we present \textbf{LEIQ-Assessor}, a multi-dimensional quality assessment model for low-light image enhancement based on multi-task learning, developed for the QoMEX 2026 Grand Challenge on Low-light Enhanced Image Quality Assessment. Specifically, our method leverages a pre-trained SigLIP2 Vision Transformer as the backbone and simultaneously predicts the overall Mean Opinion Score (MOS) together with six perceptual sub-attributes: lightness, color fidelity, noise level, exposure quality, naturalness, and content recovery. By jointly optimizing these correlated objectives via the PLCC loss, the shared representation captures richer quality-aware features than its single-task counterpart. Experiments on the MLE benchmark demonstrate that LEIQ-Assessor significantly outperforms existing no-reference IQA models and hand-crafted quality descriptors. Our method achieved second place in the QoMEX 2026 Grand Challenge on Low-light Enhanced Image Quality Assessment. The code is available at https://github.com/sunwei925/LEIQ-Assessor.

Predicting a material's properties from its structure is a central, fast-advancing problem in computational materials science. A decade of work has produced standard public benchmarks and many published machine-learning models for the task (Dunn et al., 2020). The task's fixed metric and these baselines make it a natural setting for autonomous agent research (Karpathy, 2026). On the MatBench band-gap benchmark ($>$100k crystals), a general-purpose coding agent autonomously built the most accurate model trained without external pretraining, ahead of all seventeen expert-designed models reported for the task. A closer analysis shows it reached this by implementing known methods: either already standard in crystal neural-network models, or borrowed from other areas of machine learning. The contributing implementations include element-pair features on each message-passing edge and a crystal space-group embedding. The work not only demonstrates that LLM-agent autonomous research can optimize an expert-designed machine learning model for material property prediction, but also investigates the limitations of such autonomous research.

Benchmarks of machine learning models often include many datasets, making evaluation expensive. For efficiency, it is preferable to perform evaluations on small, representative datasets instead. The selection of such subsets typically relies on heuristics and is rarely analyzed for the robustness of the resulting model rankings. We introduce a framework to perform the task of selecting datasets subsets with an evaluation of how different selection strategies preserve the global model rankings. Our framework includes bootstrap aggregation, which provides valid confidence intervals, allowing a principled comparison of selection strategies. We consider clustering, design criteria (A/D-optimality), random baselines, and greedy farthest-first (FAFI). For the latter, we derive upper bounds on selection quality in terms of ranking errors as a function of the number of selected datasets. Empirically, in time series classification (TSC, 112 datasets) and in a supplementary natural language processing benchmark derived from MTEB (57 tasks), several selection strategies improve rank preservation compared with random subsets, including simple FAFI. In contrast, in recommender systems (30 datasets), the improvement of strategies over random selection is small and typically statistically insignificant. For TSC, our best-performing strategy achieves a Spearman correlation of 0.95 with the full benchmark model rankings using only five selected datasets. Additional experiments indicate that the effectiveness of selection approaches depends on both the quality of dataset representations and the scale of the benchmarking regime.

Configuring the hyperparameters of Mixed-integer programming (MIP) solvers is a high-dimensional, instance-dependent optimization problem where suboptimal settings can degrade solving time by orders of magnitude. Default configurations are often suboptimal, while traditional tuning methods either suffer from the ``cold-start'' problem and inefficient search or heavily rely on expert experience. This paper introduces \textbf{GRIMIP} (\textbf{\underline{G}}eneral \textbf{\underline{R}}easoning for \textbf{\underline{I}}nstance-specific \textbf{\underline{MIP}} configuration), a novel hybrid intelligence framework that synergistically integrates the semantic reasoning capabilities of Large Language Models (LLMs) with the sample-efficient search of Bayesian Optimization (BO). GRIMIP enables the LLM to function as a complete probabilistic surrogate within the BO loop, significantly improving performance and reducing sampling and evaluation costs. On seven benchmarks including MIPLIB, GRIMIP achieves over 40% reduction in Primal-Dual Integral on hard instances, outperforming SMAC and other LLM-assisted BO methods. By granting LLMs sufficient autonomy, GRIMIP combines the expert-level reasoning of LLMs with the efficient search of BO, achieving state-of-the-art performance.

Closed-loop Auto Research extends automated machine learning from fixed-dataset fitting to changing the research workflow, with language-model agents editing representations and model code and acquiring external evidence. Molecular property prediction spans many small endpoints. We ask whether this action space yields improvements generalizing beyond the validation signal selecting them. We isolate three Auto Research axes, features, models, and external evidence, under a file-level ablation lock attributing each gain to one axis over a strong baseline. Across 36 endpoints in three benchmark suites we score each selected configuration once on a held-out test whose labels the search never read. A routed pipeline taking each endpoint's best validation axis reaches positive held-out gains of 0.013, 0.011, and 0.042, the transferable axis differing by suite, data on TDC, model on Polaris, feature and model on MoleculeNet. The largest model-search gain falls from 0.041 on validation to 0.003 on test, while curated data reaches 0.022 but negative 0.019 on test, two non-transfer signatures. Curated external data raises held-out CYP2C9-substrate performance by 0.17 and half-life by 0.08, admitted through a contamination filter rejecting same-source files overlapping 64 to 89 percent of test structures, necessary but not sufficient for transfer. A matched-trial automated machine learning control did not reproduce the agent's code-level model intervention, reaching 0.006 against 0.042, and the pipeline stays competitive with an 84M-parameter pretrained 3D model on the shared training split. The experiments stay within molecular property prediction, but separating discovery from held-out certification is a domain-agnostic lesson for any closed-loop system optimising a proxy for a held-out quantity.

Symbolic regression via genetic programming routinely fails on small, wide datasets - a regime common in clinical-trial monitoring, biostatistics, and engineering pilot studies - by converging on bloated, overfit expressions that exploit correlation rather than prediction. We present Evolutional Math, an open-source genetic programming system that combines four design choices to yield compact, interpretable formulas in this regime. First, fitness is measured by R-squared on held-out cross-validation folds rather than Pearson correlation on the training set, eliminating single-variable shortcuts that correlate but mis-scale. Second, a multi-island architecture runs independent populations seeded with distinct operator subsets (algebraic, logarithmic, trigonometric, and full) with ring-topology migration every M generations, preventing the search from collapsing into one region of formula space. Third, a structural deduplication scheme treats formulas differing only in constants as equivalent, so the elite archive contains structurally distinct candidates rather than near-duplicate variants. Fourth, top-k individuals undergo numerical constant refinement via scipy L-BFGS-B after each migration phase, decoupling structure search from parameter fitting. We evaluate the system on synthetic benchmarks of the form log(x_i) * x_j / (x_k * c), trigonometric mixtures, and an anonymized clinical site-monitoring dataset with 24 rows and approximately 290 candidate numeric features. The system consistently recovers compact ground-truth structures with R-squared at or above 0.99 within tens of thousands of unique formula evaluations. A reference implementation is released under a noncommercial source-available license.

Reliable benchmarking is critical for developing machine learning models for tandem mass spectrometry (MS/MS) based molecule discovery. Subtle issues in experimental design and model evaluation procedures can degrade the trustworthiness of such benchmarks and lead to erroneous conclusions. We conduct a thorough review of model evaluation issues in the recent MS/MS machine learning literature, using the standard MassSpecGym benchmark suite as a case study to illustrate the impact of these issues. We find evaluation issues in at least 17 of 26 papers reporting MassSpecGym benchmark results in the first year of its adoption. We isolate three classes of failures: (i) data leakage, (ii) shortcut learning, and (iii) implementation bugs and metric divergence. Through extensive experimentation and code replication, we quantify the impact of these issues and show how they corrupt the evaluation standards MassSpecGym was designed to enforce. We distill our findings into recommendations generalizable to MS/MS challenges, benchmarks, and custom evaluation setups. We also release MassSpecGym v1.5, an implementation of our recommendations in the MassSpecGym benchmarking suite which addresses the failure modes identified in this audit. MassSpecGym v1.5 is publicly available at https://github.com/pluskal-lab/MassSpecGym.

Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly little overfitting in practice. An attractive hypothesis is that successful ML strategies are highly compressible. We study this in the setting of LLM-driven research agents, where the hypothesis becomes directly testable via two complementary information bottlenecks. In \emph{output compression}, an exploration agent adaptively searches for high-performance models using a validation set, and we test whether a fresh ``reproducer agent'' can reproduce its performance given only an extremely short prompt and the training data. In \emph{input compression}, the explorer receives only one-bit feedback indicating whether each submitted model improves on the running best. Across 8 datasets spanning tabular classification, vision, language modeling, diffusion modeling, and reward modeling, we find that these bottlenecks have little effect on performance: short prompts and compressible feedback are sufficient to reproduce and find high-performance models. The hypothesis is falsifiable: when we deliberately induce validation-set overfitting, the results fail to reproduce with short prompts. Taken together, our results support a description-length explanation for the lack of overfitting in benchmark-driven ML: successful strategies occupy a low-complexity region of strategy space.

Equation discovery aims to automate the discovery of scientific models in the form of mathematical equations from data. Technically, equation discovery is implemented by symbolic regression algorithms. Performance of symbolic regression for equation discovery is measured along two dimensions: Prediction accuracy on test data, and recovery of known groundtruth formulas. For standard regression, accuracy is typically measured on in-domain test data, for instance, by splitting a data set randomly into training and test data. While this makes sense for in-domain interpolation, which is the common goal in ordinary regression, it can be a misleading proxy for true model discovery and generalization. The obvious alternative is to measure out-of-domain accuracy. However, obtaining challenging out-of-domain test data is a non-trivial problem. Therefore, we focus on equation recovery for evaluating symbolic regression algorithms for equation discovery. The rationale is that symbolic regression algorithms that perform well in recovering known groundtruth formulas are good candidates to perform well in unknown equation discovery. Existing benchmarks for symbolic regression include equation recovery tasks, however, with only a small number of groundtruth formulas that are publicly known. Moreover, these benchmarks place less emphasis on evaluating the robustness of algorithms in terms of their behavior under changing dimensionality, sampling size, sampling distribution and sampling domain. This, however, is of central importance to practitioners wanting to discover equations for modeling natural phenomena, since data is almost certainly noisy and comes from diverse domains, distributions, and sample sizes. To fill this gap, we introduce the Equation Recovery Benchmark (ERBench), a new evaluation framework designed to rigorously assess algorithms explicitly targeting the task of equation discovery.

Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from inter-branch information isolation, memoryless search, and lack of hierarchical control, which together hinder long-horizon optimization. We present MLEvolve, an LLM-based self-evolving multi-agent framework for end-to-end machine learning algorithm discovery. By extending tree search to Progressive MCGS, MLEvolve enables cross-branch information flow through graph-based reference edges and gradually shifts the search from broad exploration to focused exploitation with an entropy-inspired progressive schedule. To allow the agent to evolve with accumulated experience, we introduce Retrospective Memory, which combines a cold-start domain knowledge base with a dynamic global memory for task-specific experience retrieval and reuse. For stable long-horizon iteration, we further decouple strategic planning from code generation with adaptive coding modes. Evaluation on MLE-Bench shows that MLEvolve achieves state-of-the-art performance across multiple dimensions including average medal rate and valid submission rate under a 12-hour budget (half the standard runtime). Moreover, MLEvolve also outperforms specialized algorithm discovery methods including AlphaEvolve on mathematical algorithm optimization tasks, demonstrating strong cross-domain generalization. Our code is available at https://github.com/InternScience/MLEvolve.

Large-scale hyperparameter optimization (HPO) in automated machine learning (AutoML) consumes substantial computational resources, raising growing concerns about scalability and energy efficiency. Existing methods use prior information heuristically to accelerate both black-box and multi-fidelity settings, but they lack a characterization of how prior informativeness quantitatively reduces sample complexity. In this work, we provide the first distribution-dependent sample complexity bounds for multi-fidelity HPO with priors through the formal lens of fixed-budget best-arm identification. By modeling priors directly over arm means as configuration performance, we derive explicit, distribution-dependent error bounds that quantify the relationship between priors and evaluation budget. Our analysis shows that informative priors, which concentrate probability mass on near-optimal arms, yield reductions in the number of required evaluations, whereas baseline performance is recovered with uninformative or misleading priors. We conduct proof-of-concept experiments on a synthetic benchmark and on LCBench, a common multi-fidelity HPO benchmark for deep learning, to confirm our theoretical results, achieving up to 90% budget reduction while retaining solution quality. Together, our results provide a principled foundation for prior-guided and compute-efficient green AutoML.

Scaling laws provide a fundamental framework for understanding the performance of Language Models (LMs), yet deriving them requires prohibitively expensive evaluations across thousands of checkpoints or millions of inference samples. To address this, we introduce Item Response Scaling Laws (IRSL), a unified framework that integrates Item Response Theory (IRT) within the scaling law framework. Unlike traditional approaches that treat each model-benchmark pair in isolation, IRSL disentangles latent model ability from question characteristics, factorizing the scaling law estimation for $M$ models and $N$ questions to significantly reduce parameter complexity from $O(M \times N)$ to $O(M + N)$. We instantiate IRSL with Beta-IRT, which leverages the empirical probability responses of LMs -- such as token probabilities in pre-training and pass rates in test-time sampling -- to capture richer signals than binary responses. We validate our approach across two prevalent scaling paradigms: (1) pre-training downstream scaling, using 6,612 LM checkpoints and 37,682 questions from 10 benchmarks; and (2) test-time scaling, using 12 LMs and 120 questions from 4 benchmarks with up to 2,500 samples per question. Given a one-time calibration on existing model responses, IRSL yields more reliable scaling estimates using only 50 questions per benchmark (a 99.9% reduction), achieving comparable or superior decision accuracy to traditional approaches. Furthermore, we show that the estimated latent model abilities are generalizable, enabling accurate performance forecasting across benchmarks that share the same measurement objective.

Industrial Prognostics and Health Management (PHM) provides a representative case study for a broader challenge in applied machine learning: translating published papers into executable, benchmark-ready implementations. Reproducing under-specified methods in PHM is particularly difficult due to restricted access to industrial datasets, incomplete reporting of preprocessing and evaluation protocols, and implicit design choices (e.g., windowing, target construction, data splits) that critically affect performance. Existing paper-to-code systems generate implementations for individual papers, but these artifacts are often not directly comparable due to inconsistencies in assumptions and evaluation settings. We introduce \emph{agentic, framework-based PHM paper reproduction}, where an agent translates a paper into a shared PHM benchmark framework via a \emph{slot-binding interface}. This interface maps equations and protocol descriptions into structured components (task definitions, dataset adapters, windowing, targets, models, and evaluators), while explicitly recording unresolved assumptions. The resulting implementations are validated against standardized task contracts and evaluation hooks, enabling consistent and comparable benchmarking. We evaluate this approach on 16 PHM papers, comparing framework-enhanced, skill-based and prompt-based agentic reproduction against a recent framework-free paper-reproduction agent. We assess reproduction success, model-based code evaluation, framework binding of paper assumptions, and cross-paper benchmark comparability under standardized protocols. Our results show that coupling agentic generation with a shared framework transforms paper reproduction from isolated code synthesis into executable, assumption-aware, and systematically comparable benchmark implementations.

We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has $225.8$B total parameters ($23.4$B activated per token) and XS.2 has $33.4$B total ($3$B activated). Both models were trained from scratch end-to-end inside the same internal system that we refer to as our Model Factory: a tightly-integrated stack of versioned data, training, evaluation, and inference components that turn model development into an industrial process. We describe the principles and design choices of the Model Factory and also detail the end-to-end training process of our models, throughout pre-training data and architecture, post-training stages, evaluation, and quantization. On agentic software engineering and terminal benchmarks (SWE-bench Verified, SWE-bench Multilingual, SWE-Bench Pro, and Terminal-Bench 2.0) M.1 and XS.2 are competitive with state-of-the-art open models in their respective weight classes. Laguna XS.2 weights are released under Apache~2.0 at https://huggingface.co/collections/poolside/laguna-xs2.

Inverse design of materials has significantly advanced target-driven formulation optimization, yet existing materials machine learning benchmarks remain limited to forward property prediction, failing to systematically evaluate inverse optimization and generation algorithms, a critical gap that hinders the progress of target-driven materials design. To address this limitation, we propose MatFormBench, a novel benchmarking ecosystem tailored to evaluate and guide generative strategies for target-driven formulation. MatFormBench integrates a physics-driven formulation generation scheme to generate synthetic samples that faithfully emulate realistic materials structure-property response relationships, complemented by five escalating difficulty levels to quantify the complexity of these relationships. To rigorously assess algorithm performance, we further propose MatFormScore, a multi-dimensional metric that comprehensively quantifies performance across five critical axes: target success, search efficiency, exploratory capacity, robustness, and stability. We validate MatFormBench by evaluating 39 diverse inverse design algorithms, covering classical surrogate-assisted black-box search, state-of-the-art deep generative models, and increasingly popular Large Language Model (LLM)-based recommendation strategies. Across 1170 standardized algorithm-task evaluations, diffusion-based models demonstrate the strongest overall performance, while Variational Autoencoder (VAE)-based and Genetic Algorithm (GA)-based methods exhibit distinct advantages in specific scenarios. By establishing a unified evaluation standard for target-driven materials formulation, MatFormBench enables reproducible benchmarking, principled algorithm comparison, and diagnostic analysis of inverse design strategies, providing a foundational tool for advancing materials inverse design.

LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for designing their individual components and provide no guarantee that the search converges. We introduce SMCEvolve, which recasts program search as sampling from a reward-tilted target distribution and approximates it with a Sequential Monte Carlo (SMC) sampler. From this view, three core mechanisms emerge as principled components: adaptive parent resampling, mixture of mutation with acceptance, and automatic convergence control. We further provide a finite-sample complexity analysis that bounds the LLM-call budget required to reach a target approximation error. Across math, algorithm efficiency, symbolic regression, and end-to-end ML research benchmarks, SMCEvolve surpasses state-of-the-art evolving systems while using fewer LLM calls under self-determined termination. The code is available at https://github.com/kongwanbianjinyu/SMCEvolve.

Machine learning research increasingly bifurcates into two disconnected modes: benchmark-driven engineering that prioritizes metrics over understanding, and idealized theory that often fails to transfer to modern systems. In this position paper, we argue that the field focuses too heavily on these endpoints, neglecting the central scientific object: the idea. We propose an Ideas First framework in which ideas are valued for the behavioral signatures they predict in modern models, and these signatures are tested through tailored experiments designed to detect the relevant patterns rather than to win leaderboards. This shift not only bridges the gap between theory and practice but also promotes equity by removing the "complexity premium," enabling rigorous scientific contributions from researchers with modest computational, financial, and human resources. Ultimately, we advocate for a research culture centered on ideas, treating benchmarks and theorems as instruments for testing mechanistic hypotheses rather than as ends in themselves.

bde is a user-friendly Python package for Bayesian Deep Ensembles with a particular focus on tabular data. Built on an efficient JAX implementation of the sampling-based inference method Microcanonical Langevin Ensembles (MILE), it provides scikit-learn compatible estimators for fast training, efficient Markov Chain Monte Carlo sampling, and uncertainty quantification in both regression and classification tasks.

As model families, training recipes, and compute budgets become increasingly standardized, further gains in machine learning systems depend increasingly on data. Yet data engineering remains largely manual and ad hoc: practitioners repeatedly search for external datasets, adapt them to existing pipelines, validate candidate data through downstream training, and carry forward lessons from prior attempts. We study task-conditioned autonomous data engineering, where an autonomous agent improves a fixed learning algorithm by optimizing only the data side, including external data discovery, data selection and composition, cleaning and transformation. The goal is to obtain a stronger downstream solution while leaving the learning algorithm unchanged. To address the open-ended search space, branch-dependent refinement, and delayed validation inherent in autonomous data engineering, we propose DataMaster, a data-agent framework that integrates tree-structured search, shared candidate data, and cumulative memory. DataMaster consists of three key components: a DataTree that organizes alternative data-engineering branches, a shared Data Pool that stores discovered external data sources for reuse, and a Global Memory that records node outcomes, artifacts, and reusable findings. Together, these components allow the agent to discover candidate data, construct executable training inputs, evaluate them through downstream feedback, and carry useful evidence across branches. We evaluate DataMaster on two types of benchmarks, MLE-Bench Lite and PostTrainBench. On MLE-Bench Lite, it improves medal rate by 32.27% over the initial score; on PostTrainBench, it surpasses the instruct model on GPQA (31.02% vs 30.35%).

Meta-learning for algorithm selection relies on a meta-dataset in which each row corresponds to a supervised learning dataset described by meta-features and labelled with a target value that is associated with algorithm choice (typically, some function of algorithm performance). A persistent limitation is that the number of curated real-world datasets is small, resulting in sparse meta-datasets that constrain meta-learner generalisation. In this paper, we address this problem by augmenting the meta-dataset with synthetic regression datasets produced via a large language model (LLM), with generation steered toward target regions of a low-dimensionality performance space. In our experiments, we adopt a two-dimensional geometric setting defined by the cross-validated $R^2$ scores of two anchor algorithms, known as landmarkers. We compare two augmentation strategies: (1) uniform sampling, which distributes synthetic datasets across the performance space; and (2) margin-based sampling, which concentrates them near the decision boundary where landmarker preference is most ambiguous. Across 42 real-world UCI regression datasets and 730 synthetic datasets, both strategies substantially improve meta-learner performance over the unaugmented baseline under regression and multi-label evaluation formulations. However, uniform augmentation consistently outperforms margin-based augmentation, achieving a 17.47% relative reduction in Hamming loss, a 100.41% relative improvement in subset accuracy, and a +6.09% relative gain in pooled out-of-fold $R^2$. These results lead us to postulate a central thesis: the performance of algorithms resides on a low-dimensional performance manifold, whose reconstruction bias may be minimised by user-guided LLMs that seek to maximise uniform $ε$-cover, and consequently, lead to improved meta-learning for algorithm selection.

In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that starts at idea generation and ends with executable code. Our system combines structured meta-prompt engineering with executable code generation to create new ML classifiers. The OMEGA framework has been utilized to generate several novel algorithms that outperform scikit-learn baselines across a robust selection of 20 benchmark datasets (infinity-bench). You can access models discussed in this paper and more in the python package: pip install omega-models.

Support vector machines (SVMs) are a standard tool for binary classification, but their classical formulations are purely data-driven and offer no direct way to encode trusted benchmark models or structured preferences on selected subsets of the data. We propose Elite-Driven Support Vector Machines (EDSVM), a general framework that augments regularized empirical risk minimization by guiding the slack variables for a curated set of elite observations (typically the union of support vectors from one or more reference SVMs). EDSVM combines the usual slack loss with a deviation penalty that shrinks new slacks toward benchmark slack values, defining a localized, margin-aligned notion of proximity to reference models, unlike global function penalties in knowledge distillation or teacher-student methods, and without requiring privileged features as in SVM+/LUPI. Within this framework we develop two concrete models, C-EDSVM and LS-EDSVM, based respectively on hinge-type and squared-slack losses. For both variants we derive dual quadratic programs that can be implemented with modest modifications of standard SVM solvers, and we give simple sufficient conditions under which the induced margin losses are classification calibrated. Simulation studies and experiments on several UCI benchmarks show that EDSVMs closely track the behaviour induced by reference SVMs while achieving predictive performance that is competitive with, and sometimes better than, C-SVM, LINEX-SVM, and LS-SVM.

Deploying machine learning models under production constraints requires joint optimization over model family, quantization scheme, runtime backend, and serving configuration. This induces a hierarchical mixed-variable search space in which many configurations are invalid: evaluations may crash, exceed memory limits, or violate latency constraints. Standard black-box optimizers such as Tree-structured Parzen Estimators (TPE) and constrained Bayesian optimization are effective when valid configurations are common, but they can spend a large fraction of a small evaluation budget on invalid or uninformative trials in hostile deployment spaces. This paper studies that regime and asks whether optimization should be decomposed into an explicit exploration stage followed by model-guided exploitation. We propose Thermal Budget Annealing (TBA), a feasible-first exploration procedure that maps valid and feasible regions before warm-starting TPE. The method includes two robustness mechanisms for hostile hardware: trial timeouts that abort clearly infeasible evaluations early, and subspace blacklisting that temporarily suppresses categorical subspaces after repeated failures. We also introduce DeployBench, a benchmark suite for deployment optimization with hierarchical structure, hidden crash zones, hard constraints, and unequal evaluation costs. On synthetic benchmarks and real GPU deployment with five pre-trained vision models across five GPU targets (NVIDIA H100, A100, RTX 5080, L4, and T4), the proposed hybrid improves model-family discovery under tight constraints while reducing wasted budget relative to cold-start TPE.

Indonesian marketplace reviews mix standard vocabulary with slang, regional loanwords, numeric shorthands, and emoji, making lexicon-based sentiment tools unreliable in practice. This paper describes a two-track classification pipeline applied to the PRDECT-ID dataset, which contains 5,400 product reviews from 29 Indonesian e-commerce categories, each labeled for binary sentiment (Positive/Negative) and five-class emotion (Happy, Sad, Fear, Love, Anger). The first track applies TF-IDF vectorization with a PyCaret AutoML sweep across standard classifiers. The second track is a PyTorch Bidirectional Long Short-Term Memory (BiLSTM) network with a shared encoder and two task-specific output heads. A preprocessing module applies 14 sequential cleaning steps, including a 140-entry slang dictionary assembled from marketplace corpora. Four configurations are benchmarked: BiLSTM Baseline, BiLSTM Improved, BiLSTM Large, and TextCNN. Training uses class-weighted cross-entropy loss, ReduceLROnPlateau scheduling, and early stopping. Both tracks are deployed as Gradio applications on Hugging Face Spaces. Source code is publicly available at https://github.com/ikii-sd/pba2026-crazyrichteam.

Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently informative set of pilot experiments is already a major budget-allocation problem rather than a routine preprocessing step. We formulate scaling-law fitting as budget-aware sequential experimental design: given a finite pool of runnable experiments with heterogeneous costs, choose which runs to execute so as to maximize extrapolation accuracy in a high-cost target region. We then propose an uncertainty-aware method for sequentially allocating experimental budget toward the runs most useful for target-region extrapolation. Across a diverse benchmark of scaling-law tasks, our method consistently outperforms classical design-based baselines, and often approaches the performance of fitting on the full experimental set while using only about 10% of the total training budget. Our code is available at https://github.com/PlanarG/active-sl.

Benchmark hacking refers to tuning a machine learning model to score highly on certain evaluation criteria without improving true generalization or faithfully solving the intended problem. We study this phenomenon in a generic machine learning contest, where each contestant chooses two types of effort: creative effort that improves model capability as desired by the contest host, and mechanistic effort that only improves the model's fitness to the particular task in contest without contributing to true generalization. We establish the existence of a symmetric monotone pure strategy equilibrium in this competition game. It also provides a natural definition of benchmark hacking in this strategic context by comparing a player's equilibrium effort allocation to that of a single-agent baseline scenario. Under our definition, contestants with types below certain threshold (low types) always engage in benchmark hacking, whereas those above the threshold do not. Furthermore, we show that more skewed reward structures (favoring top-ranked contestants) can elicit more desirable contest outcomes. We also provide empirical evidence to support our theoretical predictions.

Automated classification of electrocardiogram (ECG) signals is a useful tool for diagnosing and monitoring cardiovascular diseases. This study compares three traditional machine learning algorithms (Decision Tree Classifier, Random Forest Classifier, and Logistic Regression) and three deep learning models (Simple Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Complex CNN (ECGLens)) for the classification of ECG signals from the PTB-XL dataset, which contains 12-lead recordings from normal patients and patients with various cardiac conditions. The DL models were trained on raw ECG signals, allowing them to automatically extract discriminative features. Data augmentation using the Stationary Wavelet Transform (SWT) was applied to enhance model performance, increase the diversity of training samples, and preserve the essential characteristics of the ECG signals. The models were evaluated using multiple metrics, including accuracy, precision, recall, F1-score, and ROC-AUC. The ECG-Lens model achieved the highest performance, with 80% classification accuracy and a 90% ROC-AUC. These findings demonstrate that deep learning architectures, particularly complex CNNs substantially outperform traditional ML methods on raw 12-lead ECG data, and provide a practical benchmark for selecting automated ECG classification models and identifying directions for condition-specific model development.

The rise of autonomous AI agents suggests that dynamic benchmark environments with built-in feedback on scientifically grounded tasks are needed to evaluate the capabilities of these agents in research work. We introduce Stargazer, a scalable environment for evaluating AI agents on dynamic, iterative physics-grounded model-fitting tasks using inference on radial-velocity (RV) time series data. Stargazer comprises 120 tasks across three difficulty tiers, including 20 real archival cases, covering diverse scenarios ranging from high-SNR single-planet systems to complex multi-planetary configurations requiring involved low-SNR analysis. Our evaluation of eight frontier agents reveals a gap between numerical optimization and adherence to physical constraints: although agents often achieve a good statistical fit, they frequently fail to recover correct physical system parameters, a limitation that persists even when agents are equipped with vanilla skills. Furthermore, increasing test-time compute yields only marginal gains, with excessive token usage often reflecting recursive failure loops rather than meaningful exploration. Stargazer presents an opportunity to train, evaluate, scaffold, and scale strategies on a model-fitting problem of practical research relevance today. Our methodology to design a simulation-driven environment for AI agents presumably generalizes to many other model-fitting problems across scientific domains. Source code and the project website are available at https://github.com/AIPS-UofT/Stargazer and https://aips-uoft.github.io/Stargazer/, respectively.

Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and evaluate algorithm discovery systems has thus far been limited by existing task suites. They suffer from many issues, such as: poor evaluation methodologies; data contamination; and containing saturated or very similar problems. Here, we introduce DiscoGen, a procedural generator of algorithm discovery tasks for machine learning, such as developing optimisers for reinforcement learning or loss functions for image classification. Motivated by the success of procedural generation in reinforcement learning, DiscoGen spans billions of tasks of varying difficulty and complexity from a range of machine learning fields. These tasks are specified by a small number of configuration parameters and can be used to optimise algorithm discovery agents (ADAs). We present DiscoBench, a fixed, small subset of DiscoGen tasks for principled evaluation of ADAs. Finally, we propose a number of ambitious, impactful research directions enabled by DiscoGen, and demonstrate its use for ADA optimisation through scaling experiments for automated prompt tuning. DiscoGen is released open-source at https://github.com/AlexGoldie/discogen.

Tandem mass spectrometry (MS/MS) is central to small molecule identification, but current deep learning systems for spectrum prediction still remain difficult to evaluate and deploy in practice. While novel architectures constantly claim state-of-the-art performance, inconsistent metadata conditioning and entangled preprocessing pipelines hinder fair architectural comparisons. Besides, existing evaluations are often restricted to curated datasets, failing to capture the heterogeneity and cross-domain shifts of real-world metabolomics. Furthermore, current benchmarks lack difficulty-aware diagnostics and leave blind to how models behave under specific compute or data constraints. To address this, we present FlexMS, a modular public-data benchmark framework that standardizes MS/MS prediction across public resources while keeping molecular encoders, metadata conditioning, predictor heads, and downstream retrieval under one protocol. FlexMS establishes a fair evaluation playground which significantly lowers the barrier for integrating new predictive tools. Rather than solely optimizing for average scores, FlexMS augments aggregate accuracy with difficulty-aware diagnostics, providing actionable guidance on model selection across different compute constraints, data scales, and downstream retrieval objectives. Ultimately, FlexMS provides the community with a reproducible standard to identify which algorithmic conclusions are stable and which operating points are most viable in practice.

The discovery of new ionizable lipids for efficient lipid nanoparticle (LNP)-mediated RNA delivery remains a major bottleneck in RNA therapeutics development. Recent advances demonstrate the potential of machine learning (ML) models to predict transfection efficiency directly from lipid structure, enabling high-throughput virtual screening and accelerating lead identification. However, as new models for LNP transfection prediction continue to emerge, the lack of rigorous and standardized benchmarking poses a significant risk and may undermine confidence in their reliability for discovery. Here, we present a robust ML benchmarking framework for evaluating transfection prediction models based on ionizable lipid structures. This framework systematically benchmarks diverse molecular representations paired with a broad range of ML architectures spanning traditional models, feedforward neural networks, and state-of-the-art graph-based methods. In addition, the presented framework supports assessment of model generalization and evaluates prediction reliability beyond standard regression metrics. Using a curated dataset of 1,100 unique ionizable lipid structures derived from the HeLa transfection dataset originally reported by Xu et al., we show that within this framework, models leveraging explicit molecular substructure encoding consistently achieve the highest predictive accuracy and should serve as essential baselines for the development of new, more sophisticated models. In contrast, some current graph-based models, including AGILE, Chemprop, and KPGT, tend to show comparatively lower accuracy. The presented framework provides a standardized, transparent, and comprehensive benchmarking resource that enables meaningful comparison of emerging architectures and establishes strong baselines for future development of predictive models in lipid-based RNA delivery.

Modern artificial intelligence is supported by machine learning models (e.g., foundation models) that are pretrained on a massive data corpus and then adapted to solve a variety of downstream tasks. To summarize performance across multiple tasks, evaluation metrics are often aggregated into a summary metric, e.g., average accuracy across 10 question-answering tasks. When aggregating evaluation metrics, it is useful to incorporate uncertainty in the aggregate metric in order to gain a more realistic understanding of model performance. Our objective in this work is to demonstrate how statistical methodology can be used for quantifying uncertainty in metrics that have been aggregated across multiple tasks. The methods we emphasize are bootstrapping, Bayesian hierarchical (i.e., multilevel) modeling, and the visualization of task weightings that consider standard errors. These techniques reveal insights such as the dominance of a specific model for certain types of tasks despite an overall poor performance. We use a popular ML benchmark, the Visual Task Adaptation Benchmark (VTAB), to demonstrate the usefulness of our approaches.