We introduce a predictive model that estimates the pre-training loss of large models from model size (N), batch size (B) and number of weight updates (K). This is the first loss prediction model that can handle changing batch size. The model outperforms Chinchilla's loss model, a model of the test loss using the batch size and number of tokens, in terms of projecting the loss at extrapolated compute budgets (up to 1000 folds). A natural use of the model is to find optimal N, B, K configurations under explicit and compound resource constraints like time, memory and compute. In our experiments, the model-selected configurations are close to ground-truth optimal. Our work advocates for loss prediction as a better alternative to heuristic-based laws, which are growing in complexity. The implementation is available on https://github.com/chuningxdy/Noisy-Quadratic-System.

Machine learning models are often required to perform well across several pre-defined settings, such as a set of user groups. Worst-case performance is a common metric to capture this requirement, and is the objective of group distributionally robust optimization (group DRO). Unfortunately, these methods struggle when the loss is non-convex in the parameters, or the model class is non-parametric. Here, we make a classical move to address this: we reparameterize group DRO from parameter space to function space, which results in a number of advantages. First, we show that group DRO over the space of bounded functions admits a minimax theorem. Second, for cross-entropy and mean squared error, we show that the minimax optimal mixture distribution is the solution of a simple convex optimization problem. Thus, provided one is working with a model class of universal function approximators, group DRO can be solved by a convex optimization problem followed by a classical risk minimization problem. We call our method MixMax. In our experi ments, we found that MixMax matched or outperformed the standard group DRO baselines, and in particular, MixMax improved the performance of XGBoost over the only baseline, data balancing, for variations of the ACSIncome and CelebA annotations datasets.

Mathematical competition problems fall into two broad types: theorem proving, which asks for a proof of a given statement, and answer construction, which requires constructing a property-satifying object with proofs. With recent advances in large language models (LLMs), formal theorem-proving techniques have made substantial progress on theorem-proving problems, yet formal answer construction remains less studied. This exposes a mismatch between current LLM model families: general LLMs are strong at informal conjecturing but are expensive and unreliable at formal proof generation, whereas prover LLMs are cheap and optimized for formal proofs but weak at mathematical reasoning for proposing candidate answers. Moreover, Lean proof checking alone does not enforce that a constructed witness is a canonical answer: circular or non-closed-form witnesses can eliminate the existential quantifier while failing to constitute an admissible contest answer. To close this gap, we introduce Enumerate-Conjecture-Prove (ECP), a neuro-symbolic framework in Lean for end-to-end answer construction with formal proofs. ECP leverages tool-assisted general LLMs to enumerate evidence and construct candidate answers, and invokes prover LLMs to produce machine-checked proofs. On PutnamBench's and autoformalized MathArena's answer-construction problems, ECP formally solves 17/346 and 18/75 instances with admissible answers and proofs, respectively, which outperform LLM baselines at aligned inference budgets. Our code is available at https://github.com/sunjia72/ecp-lpar.

Molecular dynamics (MD) simulations are computationally expensive, which is a limiting factor when simulating biomolecular systems. Adaptive sampling approaches can accelerate the exploration of the conformational space by running repeated short MD simulations from well-chosen starting points. Existing approaches to adaptive sampling have been optimized to either guide sampling in a desired direction or explore well-formed convex spaces. Here, we describe a novel adaptive sampling algorithm that leverages a k-nearest neighbor (k-NN) graph of the sampled conformational space to preferentially launch explorations from boundary states. We term this approach k-NN adaptive sampling (kNN-AS) and show state-of-the-art performance on simple and complex artificial energy functions and generalizes well on a protein test case. Implementation of kNN-AS is light, simple, and suited to complex real-world applications where the dimension and shape of the energy landscape is unknown.

Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize this data mixing problem as a bi-level objective: the best mixture is the one that would lead to the best model for a downstream objective. Unfortunately, this objective is generally intractable. In this paper, we make the observation that the bi-level data mixing objective becomes convex as our model class becomes larger. We develop and study a gradient-based approach for optimizing this convex objective, which we call MixMin, and test it on language modeling and chemistry tasks. MixMin was the only method that uniformly improved the data mixture in all our experiments. With MixMin, we improved the data mixture using less than 0.2% additional compute for a pythia-410M model trained on 8.2B tokens, resulting between 1-5% relative improvement to negative log likelihood on PIQA, ARC Easy, SciQ, and OpenWebMath. Crucially, we found that MixMin mixtures for smaller models improved training of larger models, suggesting that MixMin mixtures may be scale-invariant. When mixing bioassay data to train an XGBoost model, we saw improvements to average precision scores of 0.03-0.15.

Large Language Models (LLMs) have become increasingly capable of handling diverse tasks with the aid of well-crafted prompts and integration of external tools, but as task complexity rises, the workflow involving LLMs can be complicated and thus challenging to implement and maintain. To address this challenge, we propose APPL, A Prompt Programming Language that acts as a bridge between computer programs and LLMs, allowing seamless embedding of prompts into Python functions, and vice versa. APPL provides an intuitive and Python-native syntax, an efficient parallelized runtime with asynchronous semantics, and a tracing module supporting effective failure diagnosis and replaying without extra costs. We demonstrate that APPL programs are intuitive, concise, and efficient through three representative scenarios: Chain-of-Thought with self-consistency (CoT-SC), ReAct tool use agent, and multi-agent chat. Experiments on three parallelizable workflows further show that APPL can effectively parallelize independent LLM calls, with a significant speedup ratio that almost matches the estimation.

Designing experiments and result interpretations are core scientific competencies, particularly in biology, where researchers perturb complex systems to uncover the underlying systems. Recent efforts to evaluate the scientific capabilities of large language models (LLMs) fail to test these competencies because wet-lab experimentation is prohibitively expensive: in expertise, time and equipment. We introduce SciGym, a first-in-class benchmark that assesses LLMs' iterative experiment design and analysis abilities in open-ended scientific discovery tasks. SciGym overcomes the challenge of wet-lab costs by running a dry lab of biological systems. These models, encoded in Systems Biology Markup Language, are efficient for generating simulated data, making them ideal testbeds for experimentation on realistically complex systems. We evaluated six frontier LLMs on 137 small systems, and released a total of 350 systems. Our evaluation shows that while more capable models demonstrated superior performance, all models' performance declined significantly as system complexity increased, suggesting substantial room for improvement in the scientific capabilities of LLM agents.

Unlocking deep and interpretable biological reasoning from complex genomic data remains a major AI challenge limiting scientific progress. While current DNA foundation models excel at representing sequences, they struggle with multi-step reasoning and lack transparent, biologically meaningful explanations. BioReason addresses this by tightly integrating a DNA foundation model with a large language model (LLM), enabling the LLM to directly interpret and reason over genomic information. Through supervised fine-tuning and reinforcement learning, BioReason learns to produce logical, biologically coherent deductions. It achieves major performance gains, boosting KEGG-based disease pathway prediction accuracy from 86% to 98% and improving variant effect prediction by an average of 15% over strong baselines. BioReason can reason over unseen biological entities and explain its decisions step by step, offering a transformative framework for interpretable, mechanistic AI in biology. All data, code, and checkpoints are available at [https://github.com/bowang-lab/BioReason](https://github.com/bowang-lab/BioReason).

What property of the data distribution determines the excess risk of principal component analysis? In this paper, we provide a precise answer to this question. We establish a central limit theorem for the error of the principal subspace estimated by PCA, and derive the asymptotic distribution of its excess risk under the reconstruction loss. We obtain a non-asymptotic upper bound on the excess risk of PCA that recovers, in the large sample limit, our asymptotic characterization. Underlying our contributions is the following result: we prove that the negative block Rayleigh quotient, defined on the Grassmannian, is generalized self-concordant along geodesics emanating from its minimizer of maximum rotation less than $\pi/4$.

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between LM agents' risk awareness and safety execution abilities: while they often answer "Yes" to queries like "Is executing `sudo rm -rf /*' dangerous?", they will likely fail to identify such risks in instantiated trajectories or even directly perform these risky actions when acting as agents. To systematically investigate this, we develop a comprehensive evaluation framework to examine agents' safety across three progressive dimensions: 1) their knowledge about potential risks, 2) their ability to identify corresponding risks in execution trajectories, and 3) their actual behaviors to avoid executing these risky actions. Our evaluation reveals two critical performance gaps that resemble the generator-validator gaps observed in LMs: while agents demonstrate near-perfect risk knowledge (>98% pass rates), they fail to apply this knowledge when identifying risks in actual scenarios (with performance dropping by >23%) and often still execute risky actions (<26% pass rates). Notably, this trend persists across more capable LMs as well as in specialized reasoning models like DeepSeek-R1, indicating that simply scaling model capabilities or inference compute does not inherently resolve safety concerns. Instead, we take advantage of these observed gaps to develop a risk verifier that independently critiques the proposed actions by agents, with an abstractor that converts specific execution trajectories into abstract descriptions where LMs can more effectively identify the risks. Our overall system achieves a significant reduction of risky action execution by 55.3% over vanilla-prompted agents.

Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling. To continue scaling pretraining in this data-constrained regime, we propose that explicitly modeling and inferring the latent thoughts that underlie the text generation process can significantly improve pretraining data efficiency. Intuitively, our approach views web text as the compressed final outcome of a verbose human thought process and that the latent thoughts contain important contextual knowledge and reasoning steps that are critical to data-efficient learning. We empirically demonstrate the effectiveness of our approach through data-constrained continued pretraining for math. We first show that synthetic data approaches to inferring latent thoughts significantly improve data efficiency over training on the same amount of raw data. Furthermore, we demonstrate latent thought inference without a strong teacher, where an LM bootstraps its own performance by using an EM algorithm to iteratively improve the capability of the trained LM and the quality of thought-augmented pretraining data. We show that a 1B LM can bootstrap its performance across at least three iterations and significantly outperform baselines trained on raw data, with increasing gains from additional inference compute when performing the E-step. The gains from inference scaling and EM iterations suggest new opportunities for scaling data-constrained pretraining.

Knowing the effect of an intervention is critical for human decision-making, but current approaches for causal effect estimation rely on manual data collection and structuring, regardless of the causal assumptions. This increases both the cost and time-to-completion for studies. We show how large, diverse observational text data can be mined with large language models (LLMs) to produce inexpensive causal effect estimates under appropriate causal assumptions. We introduce NATURAL, a novel family of causal effect estimators built with LLMs that operate over datasets of unstructured text. Our estimators use LLM conditional distributions (over variables of interest, given the text data) to assist in the computation of classical estimators of causal effect. We overcome a number of technical challenges to realize this idea, such as automating data curation and using LLMs to impute missing information. We prepare six (two synthetic and four real) observational datasets, paired with corresponding ground truth in the form of randomized trials, which we used to systematically evaluate each step of our pipeline. NATURAL estimators demonstrate remarkable performance, yielding causal effect estimates that fall within 3 percentage points of their ground truth counterparts, including on real-world Phase 3/4 clinical trials. Our results suggest that unstructured text data is a rich source of causal effect information, and NATURAL is a first step towards an automated pipeline to tap this resource.

We study the problem of designing minimax procedures in linear regression under the quantile risk. We start by considering the realizable setting with independent Gaussian noise, where for any given noise level and distribution of inputs, we obtain the exact minimax quantile risk for a rich family of error functions and establish the minimaxity of OLS. This improves on the known lower bounds for the special case of square error, and provides us with a lower bound on the minimax quantile risk over larger sets of distributions. Under the square error and a fourth moment assumption on the distribution of inputs, we show that this lower bound is tight over a larger class of problems. Specifically, we prove a matching upper bound on the worst-case quantile risk of a variant of the recently proposed min-max regression procedure, thereby establishing its minimaxity, up to absolute constants. We illustrate the usefulness of our approach by extending this result to all p-th power error functions for p ∈ (2, ∞). Along the way, we develop a generic analogue to the classical Bayesian method for lower bounding the minimax risk when working with the quantile risk, as well as a tight characterization of the quantiles of the smallest eigenvalue of the sample covariance matrix.

Given a collection of feature maps indexed by a set $\mathcal{T}$, we study the performance of empirical risk minimization (ERM) on regression problems with square loss over the union of the linear classes induced by these feature maps. This setup aims at capturing the simplest instance of feature learning, where the model is expected to jointly learn from the data an appropriate feature map and a linear predictor. We start by studying the asymptotic quantiles of the excess risk of sequences of empirical risk minimizers. Remarkably, we show that when the set $\mathcal{T}$ is not too large and when there is a unique optimal feature map, these quantiles coincide, up to a factor of two, with those of the excess risk of the oracle procedure, which knows a priori this optimal feature map and deterministically outputs an empirical risk minimizer from the associated optimal linear class. We complement this asymptotic result with a non-asymptotic analysis that quantifies the decaying effect of the global complexity of the set $\mathcal{T}$ on the excess risk of ERM, and relates it to the size of the sublevel sets of the suboptimality of the feature maps. As an application of our results, we characterize the performance of the best subset selection procedure in sparse linear regression under general assumptions.

Recent advances in Language Model (LM) agents and tool use, exemplified by applications like ChatGPT Plugins, enable a rich set of capabilities but also amplify potential risks—such as leaking private data or causing financial losses. Identifying these risks is labor-intensive, necessitating implementing the tools, setting up the environment for each test scenario manually, and finding risky cases. As tools and agents become more complex, the high cost of testing these agents will make it increasingly difficult to find high-stakes, long-tail risks. To address these challenges, we introduce ToolEmu: a framework that uses an LM to emulate tool execution and enables scalable testing of LM agents against a diverse range of tools and scenarios. Alongside the emulator, we develop an LM-based automatic safety evaluator that examines agent failures and quantifies associated risks. We test both the tool emulator and evaluator through human evaluation and find that 68.8% of failures identified with ToolEmu would be valid real-world agent failures. Using our curated initial benchmark consisting of 36 high-stakes toolkits and 144 test cases, we provide a quantitative risk analysis of current LM agents and identify numerous failures with potentially severe outcomes. Notably, even the safest LM agent exhibits such failures 23.9% of the time according to our evaluator, underscoring the need to develop safer LM agents for real-world deployment.

Identifying how much a model ${\widehat{p}}_{\theta}(Y|X)$ knows about the stochastic real-world process $p(Y|X)$ it was trained on is important to ensure it avoids producing incorrect or "hallucinated" answers or taking unsafe actions. But this is difficult for generative models because probabilistic predictions do not distinguish between per-response noise (aleatoric uncertainty) and lack of knowledge about the process (epistemic uncertainty), and existing epistemic uncertainty quantification techniques tend to be overconfident when the model underfits. We propose a general strategy for teaching a model to both approximate $p(Y|X)$ and also estimate the remaining gaps between ${\widehat{p}}_{\theta}(Y|X)$ and $p(Y|X)$: train it to predict pairs of independent responses drawn from the true conditional distribution, allow it to "cheat" by observing one response while predicting the other, then measure how much it cheats. Remarkably, we prove that being good at cheating (i.e. cheating whenever it improves your prediction) is equivalent to being second-order calibrated, a principled extension of ordinary calibration that allows us to construct provably-correct frequentist confidence intervals for $p(Y|X)$ and detect incorrect responses with high probability. We demonstrate empirically that our approach accurately estimates how much models don't know across ambiguous image classification, (synthetic) language modeling, and partially-observable navigation tasks, outperforming existing techniques.

Frontier Large Language Models (LLMs) can be socially discriminatory or sensitive to spurious features of their inputs. Because only well-resourced corporations can train frontier LLMs, we need robust test-time strategies to control such biases. Existing solutions, which instruct the LLM to be fair or robust, rely on the model's implicit understanding of bias. Causality provides a rich formalism through which we can be explicit about our debiasing requirements. Yet, as we show, a naive application of the standard causal debiasing strategy, counterfactual data augmentation, fails under standard assumptions to debias predictions at an individual level at test time. To address this, we develop a stratified notion of debiasing called stratified invariance, which can capture a range of debiasing requirements from population level to individual level through an additional measurement that stratifies the predictions. We present a complete observational test for stratified invariance. Finally, we introduce a data augmentation strategy that guarantees stratified invariance at test time under suitable assumptions, together with a prompting strategy that encourages stratified invariance in LLMs. We show that our prompting strategy, unlike implicit instructions, consistently reduces the bias of frontier LLMs across a suite of synthetic and real-world benchmarks without requiring additional data, finetuning or pre-training.

Understanding how language model performance varies with scale is critical to benchmark and algorithm development. Scaling laws are one approach to building this understanding, but the requirement of training models across many different scales has limited their use. We propose an alternative, observational approach that bypasses model training and instead builds scaling laws from ~100 publically available models. Building a single scaling law from multiple model families is challenging due to large variations in their training compute efficiencies and capabilities. However, we show that these variations are consistent with a simple, generalized scaling law where language model performance is a function of a low-dimensional capability space, and model families only vary in their efficiency in converting training compute to capabilities. Using this approach, we show the surprising predictability of complex scaling phenomena: we show that several emergent phenomena follow a smooth, sigmoidal behavior and are predictable from small models; we show that the agent performance of models such as GPT-4 can be precisely predicted from simpler non-agentic benchmarks; and we show how to predict the impact of post-training interventions like Chain-of-Thought and Self-Consistency as language model capabilities continue to improve.

Graph neural networks, which typically exchange information between local neighbors, often struggle to capture long-range interactions (LRIs) within the graph. Building a graph hierarchy via graph pooling methods is a promising approach to address this challenge; however, hierarchical information propagation cannot entirely take over the role of local information aggregation. To balance locality and hierarchy, we integrate the local and hierarchical structures, represented by intra- and inter-graphs respectively, of a multi-scale graph hierarchy into a single mega graph. Our proposed MeGraph model consists of multiple layers alternating between local and hierarchical information aggregation on the mega graph. Each layer first performs local-aware message-passing on graphs of varied scales via the intra-graph edges, then fuses information across the entire hierarchy along the bidirectional pathways formed by inter-graph edges. By repeating this fusion process, local and hierarchical information could intertwine and complement each other. To evaluate our model, we establish a new Graph Theory Benchmark designed to assess LRI capture ability, in which MeGraph demonstrates dominant performance. Furthermore, MeGraph exhibits superior or equivalent performance to state-of-the-art models on the Long Range Graph Benchmark. The experimental results on commonly adopted real-world datasets further demonstrate the broad applicability of MeGraph.