arXiv preprints from January 1, 2026 through September 9, 2026 — 14:18:50 EST
Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction. In this paper, we study how LLMs learn from iterative experience at test time, a setting we refer to as Chain-of-Experience (CoE), where models accumulate...
Large-scale, high-dimensional tabular regression remains challenging: tree-based models are robust but lack end-to-end representation learning, while deep models enable flexible feature learning but often incur costly interaction modeling and sensitivity to noisy or redundant features. We propose TabNSM, a scalable regression...
Chimeric antigen receptor (CAR) T-cell therapy has transformed the treatment of B-cell acute lymphoblastic leukaemia (B-ALL). Despite high initial response rates, a substantial fraction of patients relapse, often due to loss of CAR T-cell persistence, antigen escape, or immune-privileged sites that shield tumour cells. Prolonged CAR...
Single-particle cryo-electron microscopy images a macromolecule as many noisy tomographic projections of its electrostatic potential. We reconstruct the protein backbone directly from such projections, as an atomic point cloud, without the intermediate step of reconstructing the 3D electrostatic potential map. We formulate this as an...
Preterm birth remains a major cause of neonatal morbidity and mortality worldwide. Electrohysterography (EHG), a noninvasive measure of uterine myoelectrical activity, has been studied for preterm-birth prediction, but performance estimates may be biased when segments from the same maternal record are split across training and...
Biological networks feature recurring motifs, but their uneven abundance remains poorly understood. Feed-forward loops (FFLs) are important motifs in the transcriptional networks of \textit{Escherichia coli} and \textit{Saccharomyces cerevisiae}, yet their eight types appear in highly unequal frequencies. This study presents an...
Motivation: Low-dimensional embeddings are widely used to explore cell-state heterogeneity in single-cell and other high-dimensional biological data. Although many methods preserve local neighborhoods, they may distort the apparent sampling density of processed observations, altering the visual contrast between dense and sparse...
Biomolecular design underpins applications from molecular recognition to therapeutics and synthetic biology, yet de novo interaction design remains challenging-especially for DNA/RNA, underexplored non-protein modalities with scarce, heterogeneous complex data and sharper geometric and chemical constraints. We introduce MCTH (Monte...
Deep clustering models for single-cell RNA sequencing often assign cells through latent or centroid-based mechanisms that are difficult to inspect. We introduce scDNM-VAE (single-cell Dendritic Neuron Model Variational Autoencoder), a deep clustering framework that combines a variational autoencoder with a dendritic neuron-inspired...
The emergence of organized spatiotemporal patterns is ubiquitous in oscillatory systems, from neural populations to engineered networks. Identifying these patterns and tracking how they evolve over time remains challenging, particularly when systems exhibit transient dynamics. Here, we introduce a framework based on spatial ordinal...
Competitive interactions can maintain diversity, yet coexistence is often fragile in well-mixed populations, where stochastic fluctuations can lead to extinction. This is the case in non-transitive systems, such as rock-paper-scissors dynamics, where no single type dominates globally. While spatial structure can stabilize these...
What happens when you teach an LLM-based agent the scientific method? Motivation: Scientific discovery emerges from cycles of hypothesis, implementation, empirical testing, and feedback. Can this process be automated? We approach automated algorithm design through the lens of the scientific method, where an LLM-based agent goes...
Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning about interventions, mechanisms, harms, evidence, and uncertainty. We propose a reproducible, graph-centered evaluation framework for intervention-oriented LLM behavior...
We study a dynamic coalition-formation process in the tradition of Konishi and Ray (2003): players repeatedly form and dissolve binding agreements, evaluate states by discounted long-term expected payoffs, and hold self-confirming beliefs about the process. States and payoff sharing follow Heitzig and Kornek (2018): a state is a...
Delegating cognitive operations to generative artificial intelligence redistributes execution and raises a governance problem: where human direction of the task remains. We distinguish two routes. Specified delegation places that direction before execution, through instructions, constraints, or criteria that delimit the task....
Multidimensional screening is (in)famously intractable. In this paper, we study optimal screening mechanisms subject to a tractability constraint from the agent's perspective. Specifically, we require that the menu of options offered by the designer can be ordered so that, regardless of her preference type, the agent can find a...
Trust in local institutions matters for trade, public goods provision, conflict resolution, and democratic consolidation. Using individual data from rounds 6 and 7 of the Afrobarometer surveys, I document that respondents in former British colonies are substantially more likely to trust traditional leaders than respondents in former...
This paper develops a theoretical framework for signed optimal transport. A global flatness measure induced by the continuum transport equation serves as the regularizer. We examine transport networks from a harmonic analysis perspective, prove the existence and uniqueness of the optimal coupling in the variational problem, and...
Reputation and institutional certification are the two main trust mechanisms under information asymmetry, yet their interaction remains poorly understood. We analyze nearly one million fixed-price eBay listings of Pokemon cards, where sellers choose among three signals: third-party grading (institutional certification), self-grading...
We develop a continuous-time entry-deterrence game in which market demand evolves according to the Chan-Karolyi-Longstaff-Sanders (CKLS) stochastic differential equation, allowing mean reversion and state-dependent volatility. An incumbent with privately known strength strategically chooses advertising and promotional expenditures to...
Generative AI can now perform many tasks that credentialing institutions count on to assess skill. During the AI era, do credentials retain their signaling value for subsequent performance? Mostly, yes. We audit the 2010-2026 archive of Kaggle, the largest data science competition platform, which ran two evaluation formats...
MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown that magnitude-only measurements may provide complementary information for signal recovery. However, their use in MRI reconstruction remains largely unexplored, due to lack...
In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it reproduces sampled transitions. We ask what that acceptance certifies in continuous control. We define the pipeline's danger as an expected risk and isolate its exact factor: the...
This paper presents a novel sequential policy iteration (PI) method for stochastic differential games with state- and control-dependent noise. The updates preserve mean-square stability, so that the iteration is well posed. We further derive a closed-form expression for the Fréchet derivative of the sequential PI map at a Nash...
This paper presents a method to solve the inverse problem for N-player infinite-horizon linear-quadratic (LQ) differential games with state- and control-dependent noise. For this stochastic setting, we derive necessary and sufficient conditions for linear feedback Nash equilibria, which take the form of coupled stochastic algebraic...