Science & Mathematics

Evolutionary coding agents such as AlphaEvolve are one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving and evolving programs, leveraging the prior knowledge and reasoning capabilities of LLMs. Despite their success, mutations over programs are mostly low-level upon surface heuristics, without a persistent unit of control. In contrast, science compounds through ideas. In this work, we propose ExpEvolve, which injects idea-level extraction and control into evolution: it discovers and leverages the high-level factors from programs that explain scoring differences among different programs. We characterize theoretical conditions on when discovery with idea factors improves sample efficiency. We also build a practical framework to show that the extracted high-level idea factors are helpful for guiding exploitation from experience and exploration when discovery comes to a plateau. Across 11 open-ended mathematical tasks, ExpEvolve significantly improves the final performance and sample efficiency up to 5.0x. The improvements also transfer to 4 other LLMs and to 6 machine learning tasks from MLS-Bench. Analysis shows that ExpEvolve can discover idea-level factors to provide better exploration and exploitation for evolutionary discovery.

Large language models increasingly address users in the register of care: they remember personal details, adopt a first-person emotional voice, and sustain relationships across many sessions. This anthropomorphic mode of interaction generates risks that output-level metrics capture poorly, because the same empathic utterance may console one user, entrap a second, and consolidate a delusion in a third. Governance has responded in two ways. Uniform restriction refuses sensitive requests or suppresses empathic phrasing across all outputs; group-targeted protection profiles vulnerable populations and applies stricter or prohibitive rules to them. This article argues that both fail. Uniform restriction mislocates harm in the lexical form of responses rather than in the trajectory of a relationship; group-based protection depends on a list that can never be complete, treats a fluid property as a static attribute of persons, and converts protective attention into stigmatizing labels. Drawing on philosophical work that treats vulnerability as universal, relational, and differentiated, we propose that the unit of ethical governance should be the vulnerability situation rather than the vulnerable group, develop a typology of five situations - physical, emotional, cognitive, autonomy, and relational - and specify seven principles into requirements that guide response calibration without diagnosing or persistently classifying users. The framework relocates AI safety from output control to relational safety.

Short-range hindcasts of measured wave spectra are evaluated using a recurrent model initialized by one hourly buoy spectrum and supplied with local wind, fetch and depth. Measurements from three Baltic Sea stations are combined for training in 2017--2020, validation in 2021 and testing in 2022. ERA5 reanalysis supplies winds throughout the twelve-hour prediction interval. The comparison examines supervision of spectral variance, peak frequency and peak amplitude, followed by empirical wind-sea bounds and a local relaxation constraint. Variance and peak-frequency supervision gives the lowest spectral error within the data-driven comparison, whereas additional peak-amplitude supervision gives the lowest wave-height error. In the matched physical comparison, relaxation reduces height RMSE by 5.01\% to \PhPtwoHs{}~cm. Extending this constraint through hours 13--24, without spectral targets at those hours, reduces primary spectral RMSE by 2.31\% to \PhPthreeSpec{}~$\unitE$. Upper-bound constraints increase errors. Wind-condition comparisons show spectral gains from extended relaxation in increasing, decreasing and steady strong winds, with little change in steady weak winds. The results support modest, objective-dependent benefits from local physical guidance. Wave-height scores concern the retained frequency band, and operational forecasting and transfer to independent stations remain to be evaluated.

Dynamic scheduling requires dispatching online arrivals while anticipating future jobs, as poor decisions can compound downstream costs under nonlinear tardiness objectives. We show that a pretrained large language model (LLM) can serve as the exogenous component of a structured world model, forecasting uncertain future job arrivals. Specifically, we exploit an afterstate decomposition, which separates known deterministic shop transitions from uncertain exogenous job arrivals, enabling the LLM to forecast only the latter through a compact belief representation. Building on this, we develop Afterstate World-Model Planning (AWMP), which combines an evolved, belief-conditioned dispatching strategy with short scenario-based rollouts. A surprise-triggered refresh mechanism queries the LLM only when newly observed arrivals deviate sufficiently from previous forecast, and online residual self-calibration further conditions the LLM on its recent forecast errors to handle nonstationary arrivals. Across diverse arrival distributions, AWMP reduces weighted tardiness by 6-21% on dynamic job-shop and 22-46% on flexible job-shop benchmarks, relative to the best of eight classical priority-dispatching rules.

Reliance on AI describes the behavioral patterns of when and how individuals depend on AI suggestions, and appropriate reliance patterns are necessary to achieve effective human-AI collaboration. Traditional measures often link reliance to decision-making outcomes, which may not be suitable for complex problem-solving tasks where outcomes are not binary (i.e., correct or incorrect) or immediately clear. Therefore, this study aims to develop a scale to measure undergraduate students' behaviors of using Generative AI during problem-solving tasks without directly linking them to specific outcomes. We conducted an exploratory factor analysis on 800 responses collected after students finished one problem-solving activity, which revealed four distinct factors: reflective use, cautious use, thoughtless use, and collaborative use. The overall scale has reached sufficient internal reliability (Cronbach's alpha = .84). Two confirmatory factor analyses (CFAs) were conducted to validate the factors using the remaining 730 responses from this activity and 1,173 responses from another problem-solving activity. CFA indices showed adequate model fit for data from both problem-solving tasks, suggesting that the scale can be applied to various human-AI problem-solving tasks. This study offers a validated scale to measure students' reliance behaviors in different human-AI problem-solving activities and provides implications for educators to responsively integrate Generative AI in higher education.

In sponsored-shopping auctions, one advertiser may win several positions, and a product that is never displayed may determine the prices of several winners. Under generalized second-price (GSP) pricing without self-pricing, these interactions couple allocation and payment through a single global ranking. We prove that exact autobidding equilibria under budget and return-on-investment (ROI) constraints can be computed in polynomial time whenever either the number $n$ of advertisers or the number $K$ of display slots is fixed. Our algorithms rely on two structural reductions. With few advertisers, the payment polytopes of tied bid layers combine by a Minkowski sum, giving a fixed-dimensional representation of exponentially many rankings. With few slots, budget equilibria admit threshold recovery and an exact submodular description of attainable payments at the display boundary. For ROI, we prove that every group-consecutive equilibrium has a representative with at most $K+2$ nonunit multipliers, preserving the item and price in every displayed slot. In each case, the reduction leads to polynomially many systems of polynomial equations and inequalities in bounded dimension. The algorithms compute exact multipliers and explicit distributions over valid group-consecutive rankings, with support at most $n+1$; for ROI with few slots, this improves to $\min\{n+1,K+3\}$.

We study $(\varepsilon,δ)$-differentially private synthetic data for arbitrary databases of $n$ records in $[-1,1]^d$ under a specified integral probability metric (IPM). We introduce generalized moment matching, which estimates moments privately, fits a probability measure, and samples synthetic records. A general error theorem applies when moment error controls the target IPM. This framework extends Chebyshev moment matching for $1$-Wasserstein distance and smooth queries. We apply the framework to maximum mean discrepancy with Matern and Laplace kernels and a two-layer ReLU neural tangent kernel. We also obtain guarantees for sliced Wasserstein-$1$ and the IPM induced by norm-bounded ReLU networks. With sufficiently many synthetic records,these rates are minimax optimal up to logarithmic factors for fixed dimension.

Cutting planes (cuts) remove fractional solutions from mixed-integer linear programs (MILPs) without excluding any feasible integer solutions, making them a key ingredient in modern MILP solvers. Current state-of-the-art solvers rely on fine-tuned handcrafted cut strategies, which, despite their effectiveness, remain inherently static and can be suboptimal. More recently, learning-based approaches have been proposed to design adaptive cut strategies; however, most of these methods are based on neural networks, offering limited interpretability and providing no guarantees of convergence. In this paper, we propose \emph{Genetic Programming and Statistics-based Cut Selection} (GPSCS), the first learning-based framework that explicitly generalizes handcrafted cut selection heuristics into a fully interpretable policy. First, a genetic programming model evolves a symbolic scoring function that ranks candidate cuts using features derived from the cuts and the solving context. Second, a lightweight statistics-based mechanism adaptively determines the number of top-ranked cuts to add at each separation round by detecting significant score dropouts. We evaluate GPSCS within the SCIP solver on seven classes of synthetic and real-world benchmark instances, with a strong emphasis on generalization: evaluation instances are on average 41 times harder than those used for training. Experimental results show that GPSCS improves average solving time by $6\%$ compared to SCIP's default cut selection strategy and achieves a two-fold speedup over both a recent neural-network-based approach and a no-cut baseline, demonstrating strong robustness and generalization across heterogeneous MILP families.

Large language models (LLMs) are increasingly integrated into embodied robotic planning, yet standard benchmarks primarily evaluate end-to-end task completion in nominal environments, obscuring failure origins across the execution stack. We present Alpha, a systematic fault-injection and robustness-evaluation framework for LLM-driven manipulation in simulation. Alpha injects calibrated faults across perception (sensor lag), actuation (grip slip), kinematics (unreachable targets), and planning (planner-output corruption), alongside concurrent conditions. To separate physical vulnerabilities from planner sensitivities, we introduce a matched methodology pairing an LLM agent (Llama-3 via Ollama) against a deterministic Scripted Oracle planner across a balanced 150-episode matrix under identical seeds, geometries, and safety criteria. Across the matrix, the Oracle achieves 64.0% (48/75) success while the LLM achieves 44.0% (33/75) (paired McNemar p = 3.01 x 10^-4). Crucially, excluding planner-output corruption, performance across all physical and kinematic conditions is identical: 55.0% (33/60) for both planners with zero discordant pairs (McNemar p = 1.00). This demonstrates that physical actuator slip, kinematic reach boundaries, and perceptual staleness affect deterministic controllers and LLM planners equivalently. The performance gap is driven entirely by planner-output corruption (100% Oracle vs. 0% LLM), isolating the prompt-to-JSON serialization and validation interface rather than a cognitive reasoning deficit. We also audit 169 historical pilot attempts for transparency.

The Objective Structured Clinical Examination (OSCE) is widely used to assess clinical communication skills in medical education, requiring trainees to take histories and reason clinically with standardized patients (SPs). Large language model (LLM)-based virtual standardized patients (VSPs), typically built by persona-injected prompting, offer a practical alternative. However, existing evaluations rely on a single backbone LLM, small human rater panels, or LLM-as-a-judge scoring without an utterance-aligned human-expert reference, and so cannot identify the specific shortcomings of individual models. We evaluated four LLMs (GPT-4o, Claude 3.5 Sonnet, Llama-3.1 70B, and HyperCLOVA X), spanning commercial, open-source and Korean-developed models, against a human-expert reference across three Korean OSCE cases (hematuria, fever in pregnancy, and chronic cough). In a double-blind, fully crossed design, 17 senior medical-student raters scored every model utterance on three sentence-level and six encounter-level Likert metrics, yielding 7,480 data points. We analyzed the scores using a stratified linear mixed-effects model based on an 11-category history-taking and 3-level linguistic-form taxonomy. At the encounter level, three of the four LLMs fell 0.08 to 0.47 Likert points below the human-expert reference on Comprehensibility, Consistency and Hallucination-freeness. The difference was not statistically significant for Hallucination-freeness in Claude 3.5 Sonnet and GPT-4o, Consistency in GPT-4o, and Engagement in HyperCLOVA X. Llama-3.1 70B fell significantly below the reference on all six metrics. We also introduce a web-based OSCE platform that supports virtual practice across diverse clinical cases and continuously collects student-VSP dialogues under research and privacy consent.

Multimodal ocean modeling remains challenging due to substantial heterogeneity in data structures, physical semantics, and spatiotemporal characteristics across satellite imagery, gridded oceanographic fields, and buoy observations. Existing approaches largely focus on task-specific ocean modeling, while learning transferable representations from heterogeneous observations remains an open problem. To address this challenge, we propose YingLan, a multimodal ocean foundation model that integrates physics-attribute-conditioned dynamic encoding, Spatiotemporal Increment Coupling (STIC), and ocean-state evolution-aware pretraining. Specifically, the dynamic encoding mechanism generates adaptive input projections conditioned on physical semantics and observation characteristics, enabling flexible representation of heterogeneous ocean variables. STIC models multiscale spatiotemporal dependencies through cross-scale interactions of latent temporal increments. The pretraining strategy further combines masked observation reconstruction with temporal evolution objectives to facilitate the learning of coherent ocean-state representations across different prediction horizons. YingLan is implemented using MindSpore and trained on Huawei Ascend 910B NPUs, demonstrating its compatibility with domestic AI computing infrastructure. In a seven-day sea surface salinity (SSS) forecasting task conducted in the Shenzhen coastal waters, YingLan achieves an average RMSE of 0.687508 PSU, corresponding to relative error reductions of 0.58%, 5.31%, and 12.42% compared with LangYa, XiHe, and GloNet2, respectively. These results provide initial evidence of the model's effectiveness in regional ocean forecasting, while broader cross-task and cross-regional evaluations remain necessary to assess its generalization capabilities.

Dynamic local community detection tracks the evolving community of designated seed nodes across graph snapshots. However, it faces two critical challenges: temporal supervision uncertainty, where sparse and outdated labels fail to provide seed-specific guidance under topology changes, and unbounded error cascades, where sequential policy transfer accumulates exploration errors over long horizons. To address these challenges, we propose DISRL, a Dual-scale Incremental Semi-supervised Reinforcement Learning framework. DISRL introduces a supervision construction module that dynamically generates seed-specific guidance from sparse known communities, and a dual-scale community exploration module that stabilizes policy evolution by decoupling short-term adaptation within temporal windows from long-term parameter consolidation across windows. Furthermore, we construct a dynamic graph benchmark with diverse community evolution scenarios. Extensive experiments demonstrate that DISRL consistently outperforms state-of-the-art baselines under various dynamic settings.

Spatial reasoning requires more than access to geometric tools: a reasoner must decide when direct observation is sufficient and when to reconstruct, measure, or change reference frames. We present SpatialBrain, a framework that retains experience about these decisions while keeping its vision-language backbone fixed. The key distinction is between evidence about a scene and experience about how to reason with that evidence. 3DFusionMemory fuses current-scene observations into queryable spatial relations. A Spatial Skill Library provides reusable tool procedures, and Spatial Cognition associates task conditions with experience about when and how to use memory and skills. Completed trajectories are abstracted into process records and consolidated between task blocks, allowing later decisions to draw on earlier execution without transferring scene coordinates or reference answers. Across five spatial-reasoning benchmarks, SpatialBrain improves on direct answers from the same backbone on four and ties on the fifth. Component comparisons, experience-coverage curves, and traced resource decisions characterize how the framework accumulates and uses these resources.

Vision-language models are now routinely tested on theory of mind: whether they can work out what another person sees, knows, and means. A common design asks the model to report that perspective and then to act for the person, and reads a correct report beside a wrong action as a failure to use the perspective. That reading rests on a quiet assumption: that asking for the report leaves the action unchanged. We show that it does not. In a rendered Director Task, a partition hides the largest block from a director who asks for "the largest block". Asking first which blocks the director can see raises the share of replies that choose this hidden block by 12 to 88 percentage points on six GPT models and by 17 on Qwen3.8-27B, even though the models mostly report correctly which blocks the director sees. Reasoning traces and prompt rewordings suggest why: the question shifts how the request is read, from the director's view toward the model's own. When the prompt states what the director knows and refers to, fewer than 1% of replies pair a correct report with a hidden-block choice. Any evaluation that elicits a perspective report before the action it scores needs a baseline without the question, and we deliver one: paired prompts that differ only in that question, a design any perspective-taking benchmark can adopt.

Meeting notetakers are increasingly deployed in settings where longitudinal context is available including calendar metadata, prior meetings, emails, slides, and speaker enrollments; however, meeting corpora remain limited in terms of size, domain coverage, and available context. We present OSynth, a large-scale synthetic dataset of simulated organizations comprising 570 hours of meeting audio together with associated artifacts and a latent ground-truth state. In a pairwise comparison, human raters distinguish OSynth meetings from real meeting transcripts with only 56% accuracy based on excerpts of 150-300 words. Across state-of-the-art LLMs, additional context yields significant gains on several entity-sensitive dimensions, demonstrating limitations of contemporary approaches and the potential usefulness of OSynth in developing better-contextualized meeting-understanding systems.