Research Papers

arXiv:2602.01053v2 Announce Type: replace Abstract: Role specialization in multi-LLM agent systems is often realized via multi-LoRA, where agents share a pretrained backbone and differ only by lightweight adapters. Despite sharing base model weights, each agent independently builds and stores its own KV cache for the same long, tool-augmented trajectories, incurring substantial memory and compute overhead. Existing KV cache sharing methods largely overlook this multi-LoRA setting. We observe that, cache differences across agents are dominated by adapter outputs, while activations from the shared pretrained backbone remain highly similar. Based on this observation, we propose LRAgent, a KV cache sharing framework for multi-LoRA agents. It decomposes the cache into two components, a shared base component derived from pretrained weights and an adapter-dependent component derived from LoRA weights. LRAgent reduces memory overhead by sharing the base component across agents and storing the

arXiv:2602.02239v2 Announce Type: replace Abstract: Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon. Instead, we state interpretability in deep time series models should pursue semantic alignment: predictions should be expressed in terms of variables that are meaningful to the end user, mediated by spatial and temporal mechanisms that admit user-dependent constraints. In this paper, we formalize this requirement and state that, once established, semantic alignment must be preserved under temporal evolution: a constraint with no analog in static settings. Provided with this definition, we outline a blueprint for semantically aligned deep time series models, identify properties tha

arXiv:2602.02763v3 Announce Type: replace Abstract: Interpretable time series deep learning systems are often assessed by checking temporal consistency on explanations, implicitly treating this as evidence of robustness. We show that this assumption can fail: Predictions and explanations can be adversarially decoupled, enabling targeted misclassification while the explanation remains plausible and consistent with a chosen reference rationale. We propose TSEF (Time Series Explanation Fooler), a dual-target attack that jointly manipulates the classifier and explainer outputs. In contrast to single-objective misclassification attacks that disrupt explanation and spread attribution mass broadly, TSEF achieves targeted prediction changes while keeping explanations consistent with the reference. Across multiple datasets and explainer backbones, our results consistently reveal that explanation stability is a misleading proxy for decision robustness and motivate coupling-aware robustness evalu

arXiv:2602.03018v2 Announce Type: replace Abstract: Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes algorithm and hyperparameter selection notoriously hard. Foundation models (FMs) have transformed ML, and OD is no exception: Shen et. al. (2025) introduced FoMo-0D, the first FM for OD, achieving remarkable performance against numerous baselines. This work introduces OUTFORMER, which advances FoMo-0D with (1) a mixture of synthetic priors and (2) self-evolving curriculum training. OUTFORMER is pretrained solely on synthetic labeled datasets and infers test labels of a new task by using its training data as in-context input. Inference is fast and zero-shot, requiring merely forward pass and no labeled outliers. Thanks to in-context learning, it requires zero additional work-no OD model training or bespoke model selection-enabling truly plug-and-play deployment. OUTFORMER achieves state-of-th

arXiv:2602.03912v4 Announce Type: replace Abstract: This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregressive ESN can serve as a competitive alternative to widely used forecasting methods. The study uses a two-stage design: a Parameter dataset is used to analyze ESN model configurations over leakage rate, spectral radius, reservoir size, and regularization selection, while a disjoint Forecast dataset is reserved for out-of-sample benchmarking. Forecast accuracy is measured using mean absolute scaled error (MASE) and symmetric mean absolute percentage error (sMAPE) and compared with simple benchmarks and statistical models including autoregressive integrated moving average (ARIMA), exponential smoothing state space (ETS), the Theta method, and TBATS. The model-configuration analysis reveals frequency-specific pat

arXiv:2602.05139v3 Announce Type: replace Abstract: We study bandits whose rewards depend on an unobserved Markov state that evolves independently of the learner's actions. The optimal arm can change even though the learner observes only past actions and rewards. We propose algorithms that feed LinUCB with two summaries of the hidden state: a lagged action-reward pair and, when available, a probe fingerprint formed from rewards of multiple arms. The adaptive variants refresh the fingerprint using residual, margin, and staleness tests. In synthetic stress tests over state count, transition rate, noise, and horizon, these methods reduce dynamic regret relative to standard, adversarial, and non-stationary bandit baselines when the summaries distinguish states and are updated often enough. Ablations and misspecification tests identify the main failure modes: weak fingerprint separation, high noise, and state changes during sequential probes.

arXiv:2602.06033v2 Announce Type: replace Abstract: Pre-trained vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning can improve model performance on simple physical tasks. However, fine-tuned models do not appear to learn robust physical rules that can generalize to new contexts. Based on research in cognitive science, we hypothesize that models need to interact with an environment to properly learn its physical dynamics. We train models that learn through interaction with a simulated environment using reinforcement learning. While learning from interaction allows models to improve their within-task performance, it fails to produce models with generalizable physical intuitions. We find that models trained on one task do not reliably generalize to related tasks, even if the tasks share visual statistics and physical principles, and regardless of whether the models are trained through interaction.

arXiv:2602.06837v2 Announce Type: replace Abstract: Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial interpretability. However, the unknown parameters of the scientific model cannot necessarily be estimated properly, since the flexibility of the machine learning model might make the scientific model part effectively ignored in prediction. We may avoid it by applying some regularization, but the formulation of such regularizers typically depends on model architectures and domain knowledge. In this paper, we propose an architecture-agnostic method to learn hybrid models while properly estimating the scientific parameters. The idea is to use the flatness of loss minima to achieve model simplicity, based upon the Occam's razor principle. We employ the idea of sharpness-aware minimization and adapt it to the hybrid modeling setting. Numerical experiments demonstrate the effectivene

arXiv:2602.07356v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands. However, existing steering-based alignment methods suffer from limited controllability: steering a target value often unintentionally activates other, non-target values. To characterize this limitation, we introduce value leakage, a diagnostic notion that captures the unintended activation of non-target values during value steering, along with a normalized leakage metric grounded in Schwartz's value theory. In light of this analysis, we propose NeVA, a neuron-level editing framework for controllable value alignment in LLMs. NeVA identifies sparse, value-relevant neurons and performs inference-time activation editing, enabling fine-grained control without parameter updates or retraining. Experiments show that NeVA achieves stronger target value alignment while incurring smaller perf

arXiv:2602.08646v3 Announce Type: replace Abstract: We propose a gradient preconditioning method that makes reward-guided generation with one-step generative models both efficient and reliable. Test-time noise optimization can unlock substantially better reward-guided generations from pretrained generative models, but it is prone to reward hacking that degrades quality and is often too slow for practical use. We precondition reward gradients by projecting them onto a carefully designed white Gaussian noise feasible set, a compact spectral set with blockwise norm constraints that tightly captures the statistics and spatial uncorrelatedness of white Gaussian noise. This preconditioning reshapes each gradient update into a noise-aligned direction, driving faster and more effective reward ascent while preventing reward hacking. The projection is closed-form and matches the $O(N \log N)$ complexity of FFT, adding negligible overhead in practice. In experiments on FLUX with four reward model

arXiv:2602.08689v2 Announce Type: replace Abstract: Diffusion models generate samples through an iterative denoising process guided by a pretrained neural network. Once the denoiser is fixed, the sampling algorithm itself (noise schedules, guidance scales, stochasticity profiles) still requires careful tuning, a process typically carried out through costly empirical grid search. In this work, we introduce an inverse reinforcement learning framework for learning sampling strategies without retraining the denoiser. We formulate the diffusion sampling procedure as a discrete-time finite-horizon Markov Decision Process, where actions correspond to optional modifications of the sampling dynamics. To optimize action scheduling, we avoid defining an explicit reward function and instead directly match the target behavior expected from the sampler using policy gradient techniques. We provide experimental evidence that this approach matches fine-tuned samplers and comes at a modest cost compared

arXiv:2602.09474v2 Announce Type: replace Abstract: We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode. This model captures environments that are stable except at a few vulnerable points. We introduce \emph{conditioned occupancy measures}, which remain stable across episodes even with adversarial transitions, and use them to design two algorithms. The first handles arbitrary adversarial steps and achieves regret $\tilde{O}(H S^{\Lambda}\sqrt{K S A^{\Lambda+1}})$, where $K$ is the number of episodes, $S$ is the number of state, $A$ is the number of actions and $H$ is the episode's horizon. The second, assuming the adversarial steps are consecutive, improves the dependence on $S$ to $\tilde{O}(H\sqrt{K S^{3} A^{\Lambda+1}})$. We further give a $K^{2/3}$-regret reduction that removes the need to know which steps are the $\Lambda$ adversarial steps. We also characterize

arXiv:2602.10014v3 Announce Type: replace Abstract: Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this generative, iterative procedure in a practical, finite-sample setting remains limited. We make progress toward this goal by modeling each round of self-improvement as maximum-likelihood fine-tuning on a reward-filtered distribution and deriving finite-sample guarantees for the expected reward. Our analysis reveals an explicit feedback loop where better models accept more data per iteration, supporting sustained self-improvement while explaining eventual saturation of such improvement. Adopting a task-centric view by considering reasoning tasks with multiple difficulty levels, we further prove quantifiable conditions on model initialization, task difficulty, and sample budget where easy-to-hard curricula pro

arXiv:2602.11641v2 Announce Type: replace Abstract: Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information. Although effective on in-distribution (ID) data, GNNs often fail on out-of-distribution (OOD) nodes with unseen textual or structural patterns, producing overconfident predictions without reliable OOD detection. Existing topology-driven methods mitigate node-level bias through neighboring structures, but typically encode texts as shallow features, underutilizing semantic information. Recent LLM-based approaches instead synthesize pseudo OOD priors from textual knowledge, yet suffer from two key limitations: (1) a trade-off between reliability and informativeness, where generated OOD exposures either deviate from true OOD semantics or introduce substantial ID noise; and (2) dependence on specialized architectures, limiting compatibility with topology-level advances validated in p

arXiv:2602.12080v2 Announce Type: replace Abstract: Despite recent advances in AI, event data collection in soccer still relies heavily on labor-intensive manual annotation. Although prior work has explored automatic event detection using player and ball trajectories, ball tracking also remains difficult to scale due to high infrastructural and operational costs. As a result, comprehensive data collection in soccer is largely confined to top-tier competitions, limiting the broader adoption of data-driven analysis in this domain. To address this challenge, this paper proposes PathCRF, a framework for detecting on-ball soccer events using only player tracking data. We model player trajectories as a fully connected dynamic graph and formulate event detection as the problem of selecting exactly one edge corresponding to the current possession state at each time step. To ensure logical consistency of the resulting edge sequence, we employ a Conditional Random Field (CRF) that forbids imposs