Overview

Online learning studies how to make predictions and decisions as data arrive, rather than training once on a fixed dataset. Common approaches include Online Mirror Descent and Follow-the-Regularized-Leader for optimization, exponential-weights methods for choosing among experts, and bandit algorithms when feedback is limited. Researchers analyze regret and mistake bounds in adversarial, stochastic, and changing environments, and apply these methods to areas such as forecasting, auctions, and resource allocation. A central challenge is adapting quickly to change while remaining stable and efficient when feedback is delayed, noisy, or costly.

Latest papers

145 papers17 papers in the last four weeks, down 37% on the four weeks before. 0.1% of all new papers.

Oct 2, 2026

Online Verification of Language Model Responses Under Cost Constraints

As large language models are increasingly deployed for multi-step reasoning, verifying the correctness of their outputs has become essential for maintaining reliability at scale. Verifying the correctness of large language model outputs is often done by querying a costly ground-truth oracle, which is impractical to invoke at every step in an online setting. Prior work addresses this by querying a single weak verifier on every step, and using its score to decide whether the costly strong verifier needs to be queried as well, reserving strong verification for only a small fraction of the steps. However, a single fixed weak verifier may not perform consistently well as the subject matter or difficulty of incoming queries changes over time, and committing to one in advance risks either overly costly or inaccurate verification. We introduce OMVV (Online Multi-Verifier Verification), an algorithm that maintains a pool of KK candidate weak verifiers with differing cost and verification performance, and adaptively routes each round's decision to a verifier selected via an online score combiner and an exponential-weights routing policy. OMVV provides a distribution-free, finite-time guarantee on false-accept and false-reject rates across the full pool of verifiers, and further achieves sublinear regret against the best fixed verifier in hindsight under a combined cost and consistency objective. Experiments on reasoning dataset benchmarks show that OMVV achieves higher accuracy at lower verification cost than any single fixed verifier, across a range of operating budgets.
Oct 1, 2026

Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses

Asynchronous online learning offers temporal flexibility at a structural cost: learning communities tend to fragment rather than cohere. β0β_0, the number of disconnected behavioral clusters from Zigzag Persistent Homology, serves as a cohort-level indicator of this structure. Two questions remained unverified at scale: (1) does apparent β0β_0 convergence reflect genuine behavioral alignment or learner dropout? and (2) do assessment deadlines produce reproducible fragmentation-convergence cycles? We address both across all 22 OULAD courses (N > 22,000; 857 week-pairs). Changes in β0β_0 strongly co-vary with active learner changes (pooled r = 0.387; median per-course r_delta = 0.459, 20/22 courses), identifying β0β_0 as a participation-sensitive indicator: β0β_0 and active learner counts co-respond to deadline events rather than one causing the other. Deadlines produced fragmentation in 82.6% of assessments and the full Fragment First, Converge Later (FFCL) cycle in 60.2%. 3-phase analysis confirmed structural fragmentation as the dominant long-term trajectory (90.9% of courses), moderated by curriculum structure. These findings establish β0β_0 as a participation-sensitive structural indicator with direct implications for AI-augmented learning analytics design.
Oct 1, 2026

Towards a Cloud Fog Edge System for Smart Building

In this article, we present our vision and recent advancements toward creating a decentralized system capable of learning from real-time data within buildings to support sustainable and privacy-preserving smart environments. Our approach promotes the concept of the building itself as the data center, aligning with the principles of edge computing to safeguard confidentiality and reduce reliance on external cloud infrastructure. This is particularly valuable in humanitarian contexts, where data sovereignty, energy efficiency, and infrastructure constraints are critical. We detail a lightweight, "Kubernetes-like" orchestration framework for deploying AI services within such environments and demonstrate our progress in implementing AI algorithms on low-power, cost-effective microcontrollers such as those in the Arduino ecosystem. By enabling in-situ learning directly on sensors or microcontrollers, our work aims to bring intelligent services to resource-limited settings, fostering autonomy, resilience, and sustainable development in vulnerable or underserved communities. The contributions in this article are related, firstly, to our project "Online Machine Learning Algorithms for Embedded Systems" and the evaluation of two new online algorithms. Secondly, we envision a cloud-fog-edge architecture based on the KOptim and FIWARE components, and we propose a methodology for coupling them. Experimental results of the online algorithms are also presented, showcasing real-world traces.
Sep 30, 2026

LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models

Low-Rank Adaptive Residual Connections (LARC) give a frozen model a compact numerical state that can learn from feedback. The map h+BAhh+BAh changes the hidden input to a pretrained mixer. An episode copies a learned initialization \ρ\ρ into a private state \Φ\Φ, updates its factors when feedback arrives, and resets to the bound \ρ\ρ. We analyze the factor-space updates and trace this input-side policy carrier into Orbit, the post-training realization of Memory-Mediated Learning Architecture studied here. In Orbit's released default, the learned residual shapes predictions while memory adaptation changes the retained evidence.\n\nThe controlled studies use a rank-4 residual with 12,288 factor entries on frozen MiniCPM5-1B-SFT. Two feedback updates reduce expected query execution error by 24.65 and 36.65 percentage points relative to the respective trained reset states in a four-candidate development task with 16 parameter groups and three paired seeds. A direct support-loss rule reaches 0.78125\% error. In repository-balanced chronological replay of public continuous-integration jobs, retaining updates raises half-Brier loss from 0.1274 to 0.1808. A follow-up intervention observes same-batch non-descent and inconsistent future benefit from shrinking steps. These comparisons measure when numerical state helps a later read and when the trained reference is more effective.
Sep 29, 2026

When Is Coarse Supervision Worth It? Cost-Aware Learning under Unknown Aggregation

Modern learning systems often acquire supervision at multiple resolutions, trading annotation cost against information content. We study cost-aware two-resolution learning, where expensive fine labels reveal a vector response and cheaper coarse labels reveal a scalar aggregate formed with unknown weights, while the target remains the full response. The challenge is that unknown aggregation changes which directions coarse data can identify, so the value of coarse supervision depends jointly on cost, noise, and identification. We characterize this information geometry and develop an estimate-and-track policy that learns the aggregation rule and tracks the optimal resolution mix. We derive a closed-form break-even condition for coarse supervision and prove that the online policy attains the optimal leading cumulative-risk coefficient, with a matching local asymptotic minimax lower bound. Synthetic experiments support the predicted all-fine/mixed transition, show the online learner approaching the oracle-share benchmark, and demonstrate a finite-budget gain over all-fine acquisition when coarse supervision is sufficiently favorable. Our results provide a principled way to balance information and annotation cost across supervision resolutions.
Sep 28, 2026

Improving scalable oversight with co-trained monitors

Worker-monitor setups are a promising approach to AI oversight, but training workers against fixed monitors can incentivize monitor evasion. We study whether this failure mode can be avoided by co-training the monitor alongside the worker, and explore both supervised and self-supervised approaches. In the supervised setting, we prove a characterization: monitoring is possible with vanishing error and query rates exactly when the class of possible monitor functions has finite Littlestone dimension. This connects worker monitoring with an established literature on adversarial online learning. For self-supervision, we propose a co-training procedure based on test-time distillation: the monitor uses additional test-time compute to generate training labels, then trains its standard-compute policy on those labels. For majority-vote labels, we give a finite-sample sharpening guarantee under adaptive worker distributions with action coverage, that shows that the monitor's verdicts converge to its initial modal verdicts. We stress-test the former in code-security settings where the worker is trained adversarially to fool the monitor. Our results suggest that adaptive monitors are better at keeping pace with evolving worker strategies, while fixed monitors are more vulnerable to evasion.
Sep 25, 2026

Evasion Attacks on Cost-Utility-Based Adversarial Training for Online AutoML in IoT Networks

As Internet of Things (IoT) networks increasingly depend on machine learning for anomaly, malware, intrusion detection, and network monitoring, such systems have become attractive targets for evasion attacks. Evasion attacks pose a major security risk because an adversary intentionally modifies input data to mislead a trained model into producing incorrect predictions while evading detection. This study evaluates the impact of black-box evasion attacks on a cost-utility-based adversarial training defense strategy in an Online AutoML context for IoT networks. Specifically, evasion attacks were applied to online learners, including Hoeffding Tree (HT), Leveraging Bagging (LB), Streaming Random Patches (SRP), Hoeffding Adaptive Tree (HAT), and Adaptive Random Forest (ARF). By developing naive and adversarially trained (AT) versions of these online learners, we generated clean and adversarial accuracies for each model. The results show that the AT versions of LB and SRP performed best, achieving the highest adversarial accuracy (0.985) and high clean accuracy (0.993) at the highest cost budget of 1.00, with a maximum accuracy reduction of only 0.8%. Finally, drift detection was conducted using the Early Drift Detection Method (EDDM).
Sep 25, 2026

Online Learning via Learned Latent Bayesian Tracking

Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled approach casts online learning as Bayesian state tracking, where model parameters are updated sequentially via Bayesian filtering. However, applying Bayesian filters directly to modern deep models is computationally prohibitive due to the high dimensionality of parameter space, forcing existing methods to rely on restrictive approximations or manually designed low-dimensional subspaces. In this work, we identify the absence of a suitable low-dimensional dynamical representation as the core bottleneck in Bayesian filtering-based online learning. Accordingly, we propose Adaptive Update through Representation Adaptation (AURA), a meta-learning framework that learns offline a low-dimensional latent state-space model governing the evolution of optimal model parameters under distribution shift. Online adaptation is then performed via extended Kalman filtering in this learned latent space followed by reconstruction of the full model parameters through a learned lifting map, enabling efficient single-step online adaptation while preserving model expressiveness. Evaluated on online adaptation of neural wireless receivers under time-varying channels and on non-stationary image classification, AURA shows substantial improvements in adaptation speed, accuracy, and computational efficiency over existing online learning and Bayesian filtering baselines, demonstrating that an adaptation-aware latent geometry is beneficial for effective Bayesian online learning in high-dimensional models.
Sep 24, 2026

Downside-Controlled Online Forecast Combination under Delayed and Revised Outcomes

Post-hoc correction adjusts a forecaster that cannot be retrained, such as a foundation model, but a correction fitted where errors are stable can hurt where they shift. We aim for downside control: not much worse than the starting forecast. We combine the frozen forecaster, a static corrector and an online corrector on the simplex, using only losses that mature after the horizon. Across seven benchmarks and four base models, two of them foundation models, the worst deterioration over 28 pairs at the main horizon is 0.15% and gains reach 11.5%. On day-ahead load for seven European bidding zones it lowers mean MSE in all seven zones, while single correctors raise mean MSE by up to 102% where the published forecast is most accurate. Three empirical conditions on expert speed, stream length and outcome alignment, each fixed by a documented failure, delimit its scope. Learning from the provisional outcome improves four zones on the settled one; learning on the settled outcome restores all seven.
Sep 23, 2026

Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation

A neural network's layers can be treated as time steps of a state-space model, turning Bayesian training into a smoothing problem: a forward pass propagates Gaussian moments through the network, and a backward Rauch--Tung--Striebel pass updates the weight posteriors in closed form. Such methods learn from each observation in a single pass, in an uncertainty-aware manner, and without gradient-based iterations or replay, which makes them well suited for online adaptation and data-efficient learning. Existing smoothing-based methods, however, are restricted to diagonal covariances across activations, discarding correlations between neurons. We overcome this limitation via a cross-covariance identity that enables full-covariance propagation through a network's nonlinear activations. We derive a one-step-per-layer smoother that approximates as Gaussian only each layer's affine output, and that applies both to deterministic systems with noisy observations and to stochastic systems described by output statistics. We demonstrate this method in non-stationary classification, online dynamics learning, and policy adaptation of a vision-language-action model, and find that it is generally more accurate than other smoothing-based methods.
Sep 18, 2026

Optimal Randomized Proper Online Learning

We prove that the optimal expected mistake bound of online learning a function class H\mathcal{H} by a randomized proper learning algorithm is O(L(H)log⁡T)O(\mathtt{L}(\mathcal{H}) \log T), where L(H)\mathtt{L}(\mathcal{H}) is the Littlestone dimension of H\mathcal{H} and TT is the time horizon. Our result improves upon the previously best known bound of O(L(H)log⁡6T)O(\mathtt{L}(\mathcal{H}) \log^6 T) given by Daskalakis and Golowich (STOC 2022), and is optimal up to a universal constant for worst-case classes.
Sep 17, 2026

Online Adaptive Kernel Mixing for Gaussian Process Decision Making

Gaussian Processes (GPs) are widely used as surrogates for black-box functions in sequential decision-making problems such as Bayesian optimization (BO), level set estimation (LSE), and Bayesian active learning (BAL). GP performance critically depends on kernels, and standard kernels can lead to suboptimal decisions under misspecification. To address this, we introduce HACK GPs (Hedge Adaptive Cumulative Kernels), a method that views kernel selection as an online learning with expert advice problem. HACK treats each candidate kernel as a GP "expert" and updates a distribution over experts online using AdaHedge, based on a loss received as a proxy for their ability to fit the function and align with the task objective. We provide two variants of HACK: (i) Mixture of Gaussians (MoG) and (ii) categorical sampling. We establish general guarantees showing that, under a loss-gap condition, the weight concentrates on the best kernel and the resulting acquisition function is close to that of the best expert. Empirically, we observe robust performance across BO, LSE, and BAL compared to standard kernels such as Squared Exponential and Matern-5/2, as well as simple ensemble baselines.
Sep 16, 2026

TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting

Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shift in timing and height every year, and information that helps while a wave grows misleads after its peak, whereas last season's shape stays informative for a year. Existing epidemic graph models and general forecasters read a short fixed window and treat all past information alike, so they neither exploit earlier seasons nor discard stale associations when the epidemic phase changes. To address these limitations, we propose TERN, a forecaster built around a delta-rule fast-weight memory that decays channel-wise and erases along a learned address under gates driven by local epidemic-phase features, combined with an explicit seasonal reference and online adaptation. On three Cola-GNN influenza benchmarks, TERN outperformed epidemic graph models and general forecasters, matched or exceeded seasonal references, and a controlled comparison confirmed the contribution of the memory itself.
Sep 15, 2026

Online Gradient Computation for Warping Gaussian Process Transformations

Warped Gaussian processes (GPs) handle non-Gaussian observations by mapping them into a latent standard GP via a parametric transformation called warping. Existing streaming variants, however, either optimize the warping parameters periodically or sacrifice analytical tractability for a higher model capacity. To bridge this gap, we show that the gradient of the instantaneous negative log-likelihood of a warped GP admits an exact recursive computation. Based on this result, we propose a novel online method for warped GPs that jointly updates the latent GP moments and optimizes the warping parameters.
Sep 14, 2026

Online local learning for generative thermodynamic computing

Generative thermodynamic computers turn thermal noise into structured data through Langevin dynamics. We train these systems with a local update at each integration step. The reverse-path Onsager-Machlup objective yields a coupling gradient that is a symmetric sum of local residual-state correlations. We apply this gradient immediately rather than accumulating it over a full trajectory. In digital simulations using MNIST prototypes, online and trajectory-batch training reach similar validation losses on fixed noising paths. Models trained online release less heat on average in all five independently seeded pairs, with both models' parameters held fixed during sampling. Auxiliary classifier and nearest-prototype measures change modestly, while pairwise diversity decreases. The response to noise depends strongly on where the errors enter: independent zero-mean errors in the formed updates produce little heat change over a finite range of noise amplitudes, whereas residual offset and temporal correlation have much larger effects. Storing trained couplings requires substantially less precision than resolving deterministic updates during training. Together, these results establish a local online training method and show how update timing, noise structure, and precision affect generative thermodynamic computing.
Sep 14, 2026

A Memristive Synapse for Online STDP Learning and Inference in SNNs

This work presents a fully analog memristive synaptic circuit for online spike-timing-dependent plasticity (STDP) learning in spiking neural networks (SNNs). The proposed synapse integrates a local STDP circuit generating gradual timing-dependent conductance updates directly from pre- and post-synaptic spikes. Learning occurs during normal network operation without requiring external digital control or explicit STDP waveform synthesis. Post-layout simulations of the memristive synapse implemented in a 130 nm CMOS technology show spike-timing-dependent conductance adaptation during SNN operation. A 2x2 SNN simulation further illustrates online neuron specialization through unsupervised learning.
Sep 11, 2026

Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up

False wake-up activations remain a persistent challenge in conversational AI. Speech phonetically similar to a device's wake word can produce a syntactically valid and semantically coherent ASR transcript that the assistant incorrectly executes. Most existing systems make a single intent decision in isolation, without a mechanism to learn from recurring errors over time or adapt to individual users through personalized learning. We introduce the Feedback-Driven Adaptive Self-Correcting Inference Layer (ASCIL), a complementary post-ASR correction framework that re-evaluates wake-up intent before response generation by fusing acoustic embeddings, linguistic cues, device context, and patterns from past misclassifications. ASCIL interprets implicit signals, including hesitation, disengagement, and silence, and explicit signals, including cancellation and repetition, as automatically inferred, noisy behavioral indicators of potential misclassification. These signals drive online pattern updates without manual annotation, whereas the intentional/unintentional reference labels used for offline evaluation are human-annotated. It generalizes from prior errors, applies corrective adjustments at inference time, and continuously updates in parallel with natural-language execution. Evaluated on a proprietary dataset of 3,667 interactions with human-annotated intentional/unintentional reference labels spanning 14 acoustic and contextual conditions, ASCIL achieves 54.27% relative error reduction on a session-disjoint subset constructed from baseline failures, and up to 24.39% relative error reduction at threshold 0.90 on the issue-tagged evaluation slice. These gains are achieved while improving intentional acceptance rates, with a median added latency below 60 ms in the reported benchmark.
Sep 9, 2026

An Exponential Deterministic--Randomized Gap in ERM-Oracle Complexity for Thresholds on an Unknown Order

Attias, Hanneke and Ramaswami (NeurIPS 2025) asked whether randomization provably reduces the oracle calls needed for online learning when the class is accessible only through an oracle. We study the instance they singled out: transductive online learning of thresholds on an unknown total order of T instances, with a consistency-type ERM oracle that returns a full concept consistent with a queried labeled set (or reports non-realizability). Our main result is a separation for a fixed natural oracle. When the oracle is the minimal-prefix rule (or the maximal-prefix rule), every deterministic learner makes M mistakes and Q calls with M+Q≥T−εM+Q\ge T-\varepsilon on some instance (ε∈{0,1}\varepsilon\in\{0,1\}, according to whether the empty prefix is a concept), and the constant is exact; hence O(log⁡T)O(\log T) mistakes cost T−ε−O(log⁡T)T-\varepsilon-O(\log T) calls, whereas that paper's randomized learner achieves O(log⁡T)O(\log T) expected calls and mistakes under the same rule. The randomized order is optimal: on an explicit hard distribution under the minimal-prefix rule, every learner has expected mistakes at least ((T+1−ε) 128−E[Q]−1)/2((T+1-\varepsilon)\,128^{-\mathbb{E}[Q]}-1)/2, so Ω(log⁡T)Ω(\log T) expected calls are necessary for polylogarithmic mistakes. The separation is governed by the oracle's selection rule, not by the class alone: for a legal feasible-median ERM rule a deterministic learner achieves O(log⁡T)O(\log T) calls and mistakes, while a global-median rule again forces linear total cost. The same linear bound holds when the oracle's answers are chosen adversarially and then frozen into a memoryless oracle. We add partial tradeoff results for fixed query budgets (the middle regime is open) and an interface contrast: with only a weak consistency oracle, returning a realizability bit, both deterministic and randomized learners need Θ(T)Θ(T) calls.
Sep 8, 2026

Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits

The brain uses discrete spikes for dynamic computation, yet in the fields of computational neuroscience and brain-inspired computing, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question. Dominant spiking neural network (SNN) approaches circumvent this by approximating backpropagation through surrogate gradients, decoupling learning from biological spike timing. In order to integrate seemingly incompatible spike timing and continuous gradients, we reformulate temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state. This enables an online feedback learning framework for NMCs through a gradient tunneling (GT) algorithm and the lead-lag expansion technique that derives credit assignment from local synaptic spike timing, while remaining compatible with ANN-SNN hybrid architectures. Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention, and perform comparably to leading SNN online learning methods on real-world benchmarks with far fewer parameters. The proposed framework addresses the two-decade-old NMC feedback learning problem and suggests a computational theory for the brain's temporal credit assignment mechanisms.
Sep 7, 2026

No-Regret Mixing of LRU and LFU with Optimal Switching Cost

Caching systems often rely on simple eviction policies such as Least Recently Used (LRU) and Least Frequently Used (LFU), which perform well in complementary request regimes. Recent policies such as LeCar and Cacheus combine LRU and LFU using ideas from the experts problem in online learning. Specifically, upon a miss, they randomize between the two eviction rules using probabilities derived from scores updated by tracking the history of past evictions. While these policies exhibit strong empirical performance, it remains unclear whether they are guaranteed, on every request sequence, to perform asymptotically as well as the better of LRU and LFU, i.e., whether they achieve sublinear regret with respect to this benchmark. We first show that LeCar suffers linear regret against an oblivious adversary, even with unbounded history. We then propose H-MC, a Hedge-based mixture of virtual LRU and LFU caches that preserves Hedge's selection probabilities, and hence its regret guarantees, while minimizing the switching cost among all joint selection rules with these marginals.
Sep 6, 2026

CAROL: Context-Aware Online Learning for Fuzzer Scheduling

Ensemble fuzzing runs multiple fuzzers on a target while a scheduler allocates CPU time among them. Existing schedulers base these decisions on compact summaries of past performance and rules fixed before a campaign. Our measurements reveal two limitations. First, past-reward summaries do not reliably capture performance evolution: after accounting for estimation noise, agreement between consecutive-window rankings is statistically indistinguishable from within-window self-agreement. Second, predictive signals vary across targets: on eight of nine targets, a weighting learned from the other eight predicts reward worse than one learned on the current target. We introduce CAROL, an online scheduler that uses each fuzzer's current context. Already available to the dispatch loop, this context describes reward trends, waiting and plateau time, reached code, and estimation uncertainty. CAROL uses context in two ways: a domain-guided method detects whether a fuzzer is rising or rotting and applies a phase-specific learning rule, while a learned method predicts reward from 15 context signals and uses predictive uncertainty for online selection. Across nine Magma targets, CAROL triggers more unique bugs than each of three ensemble-scheduling baselines whenever their results differ, and fewer on none. Compared with the strongest baseline for each target, CAROL gains 11.8% and surpasses an oracle that retrospectively selects the best single fuzzer per target. Removing context eliminates the gain, and the additional bugs are concentrated among those the baselines trigger rarely or never. Run unchanged on five widely used C++ programs, CAROL finds 120 previously unknown crashing defects, deduplicated by site, fault, and entry point; all were reported to maintainers through the projects' stated disclosure channels.
Aug 30, 2026

Adversarial Online Classification with a Preview

Worst-case online classification is governed by sequential complexity, such as Littlestone dimension, and can be impossible even for statistically simple classes, such as thresholds of VC dimension one. We study a preview model in which an oblivious adversary fixes an entire labeled sequence of length TT, a uniformly random subset of size pTpT is revealed before prediction begins, and the remaining (1−p)T(1-p)T examples are then presented in their original adversarial order. Against the best full-sequence hypothesis evaluated on the unrevealed examples, we characterize the dependence on the preview rate pp: for binary classes of VC dimension dd, the optimal excess loss is Θ(d/p+dT)Θ(d/p+\sqrt{dT}), up to the trivial cap at TT; for multiclass classes we obtain the corresponding O~(dDS/p+dNatT)\widetilde O(d_{\rm DS}/p+\sqrt{d_{\rm Nat}T}) bound with no dependence on the number of labels. Thus a random preview can replace worst-case sequential complexity by classical statistical dimensions without randomizing the online order. To achieve the sharp binary bound, our ChainedPrediction algorithm uses an online analogue of chaining, implemented as a multiscale aggregation algorithm rather than only as an analytic argument.
Aug 25, 2026

Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in Online Learning

The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distinct behavioral, emotional, and cognitive states. A reliable prediction requires bringing together different types of behavioral signals as well as expressive cues. Through our analysis of the CASED dataset, it is clear that engagement prediction gets even harder due to the high inter-person variability as well as the subjectivity of the engagement annotation. To tackle these challenges, we develop a multimodal framework that integrates the implicit spatiotemporal features extracted from pretrained video, audio, and image encoders along with structured behavioral modalities like head pose, gaze, facial action units, emotion, and wavelet-based audio features. We integrate these modalities via a Perceiver IO latent bottleneck. Moreover, student and instructor personalities are modeled as variational posteriors over learnable embeddings to enable partial pooling across participants. We employ evidential regression and spectral-normalized Gaussian process classification heads for uncertainty-aware prediction to further improve robustness and calibration. Benchmark on the CASED challenge test set shows that all participating methods converge near random-chance performance, revealing the difficulty of the dataset. In this highly ambiguous regime, our framework achieves competitive performance while uniquely offering well-calibrated uncertainty metrics, demonstrating that reliable risk-quantification is an essential prerequisite for deploying engagement models in real-world educational tools.
Aug 15, 2026

Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents

Learning from experience is critical for developing capable, self-improving large language model (LLM) agents. Existing methods typically extract knowledge from accumulated trajectories via reflection, memory, rules, or skills. However, agents in realistic environments continuously encounter novel tasks, often offering only a one-shot opportunity to improve. These executions yield rich but highly noisy contexts, entangling broadly useful lessons with task-specific artifacts. Critically, prior works rarely validate their effectiveness on complex real-world tasks or isolate the underlying drivers of improvement. To address these gaps, we formulate online harness learning, where a frozen agent improves by continually updating a structured harness across sequential tasks. This formulation enables a systematic study of key self-improvement factors through our proposed Evo-Harness. At its core, context-to-harness skill compilation distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation. To demonstrate the efficacy of one-shot skill compilation, we evaluate across five realistic benchmarks (TerminalBench2, SWE-bench, CL-Bench, -bench, WebArena-Infinity). Our extensive analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly. Our code is available at https://github.com/A-EVO-Lab/a-evolve/tree/release/evo-harness.
Aug 7, 2026

Dirichlet Follow-the-Leader Closes the Gap in Simultaneous Multiclass U-Calibration

Can one forecaster attain the optimal regret rate for every bounded proper loss and also adapt to every smooth proper loss? Recent work answered this up to a dimension gap. Its self-concordant perturbation gives roughly K5/4TK^{5/4}\sqrt{T} worst-case regret and incurs an additional βKlog⁡Kβ\sqrt{K}\log K for ββ-smooth losses. We close both gaps with a one-line forecaster. After observing class counts ct−1c_{t-1}, draw the next prediction from Dir⁡(ct−1)\operatorname{Dir}(c_{t-1}), on the face of classes seen so far. This is a fresh Bayesian bootstrap of the outcomes. The analysis rests on an exact identity: averaging any bounded proper loss under Dir⁡(α)\operatorname{Dir}(α) equals a discrete derivative of its Dirichlet-averaged Bayes risk. The identity makes the be-the-perturbed-leader term telescope to a nonpositive Jensen gap. A one-count likelihood ratio then bounds stability by the inverse square root of that class's count. The resulting single, horizon-free algorithm satisfies sup⁡ℓEReg⁡ℓ≤4STT≤4KT\sup_{\ell}\mathbb{E}\operatorname{Reg}_{\ell}\leq 4\sqrt{S_T T}\leq 4\sqrt{K T} and EReg⁡ℓ≤52β(1+log⁡T)\mathbb{E}\operatorname{Reg}_{\ell}\leq \frac{5}{2}β(1+\log T) for every ββ-smooth proper loss. Here STS_T is the number of observed classes. Known lower bounds show that both rates are optimal in their nontrivial regimes. The proof covers nondifferentiable losses and changes of the active simplex face.
Aug 4, 2026

Shaping Wind-Tunnel Airflow for Unmanned Aerial Vehicles using Online Learning

The development and testing of advanced aerial robots require experiments in controlled environments with tailored airflow profiles. This paper presents an online learning algorithm for controlling the complex airflow field in a multi-fan vertical wind tunnel. Our method combines a simplified physical model with iterative, measurement-based learning, enabling sample-efficient convergence to desired airflow distributions. We demonstrate the method's versatility by generating complex airflow, such as uniform, Gaussian, and parabolic profiles. Crucially, we show that our algorithm can produce an airflow profile specifically designed for passive soaring, greatly enhancing flight performance of a soaring robot. Variability, practical utility, and robustness of our approach are further highlighted by successful operation with a varying number of fans.
Jul 31, 2026

Personalizing Large Language Model Agents with Small Policy Models

Large language model (LLM) agents can retrieve memory, call tools, ask clarifying questions, and vary response style, yet adapting these execution decisions to an individual user remains difficult. Fine-tuning a separate LLM is costly or impossible for proprietary systems, while prompts and memory primarily expose user information to the agent rather than adapt its execution decisions from feedback. We formulate personalization of a frozen agent as online learning of a per-user execution policy from scalar feedback observed only for the executed action. We propose FABLE (Factorized Adaptive Bandit Layer for Execution), a lightweight policy layer outside a potentially black-box host agent. FABLE factorizes memory, information-acquisition, and response decisions so feedback updates related choices; filters actions through an externally specified feasible set before exploration; and learns user-specific residual preferences relative to a fixed default-and-cost score via Bayesian contextual Thompson sampling. Under a linear residual-reward model, a calibrated variant inherits an expected-regret bound against the best feasible action. We also characterize preferences unidentifiable under persistent feasibility constraints and provide anytime-valid false-promotion control. Across personalized-reasoning, controlled-feedback, and executable tool-use evaluations, FABLE improves several preference-sensitive behaviors relative to rule-only control while remaining competitive on end-to-end task performance.
Jul 30, 2026

Fast Rates for Swap-Agnostic Learning of Proper Losses

Swap-agnostic learning strengthens classical agnostic learning by allowing the comparator to select a different hypothesis on each level set of the learner's predictions. This benchmark captures prediction-dependent postprocessing, but appears to require solving a separate agnostic-learning problem for every possible prediction value. We show that, for proper losses, these prediction-level comparisons can instead be controlled jointly. Our main result is an offline swap-agnostic learner for any fixed proper loss. For a finite hypothesis class HH and any fixed smooth proper loss, the excess risk from mm i.i.d. samples is O~((log⁡∣H∣/m)2/3)\widetilde{O}((\log |H|/m)^{2/3}), with a corresponding online swap-regret bound of O~(T1/3(log⁡∣H∣)2/3)\widetilde{O}(T^{1/3}(\log |H|)^{2/3}). We also give algorithms whose predictions are simultaneously swap-agnostic for entire families of losses. For all proper losses bounded in [−1,1][-1,1], we obtain online and offline rates of O~(Tlog⁡∣H∣)\widetilde{O}(\sqrt{T\log |H|}) and O~(log⁡∣H∣/m)\widetilde{O}(\sqrt{\log |H|/m}), respectively. For convex, 11-Lipschitz proper losses, these rates improve to O~(T1/3(log⁡∣H∣)2/3)\widetilde{O}(T^{1/3}(\log |H|)^{2/3}) online and O~((log⁡∣H∣/m)2/3)\widetilde{O}((\log |H|/m)^{2/3}) offline. These bounds are tight up to logarithmic factors and improve upon the O~(T2/3(log⁡∣H∣)1/3)\widetilde{O}(T^{2/3}(\log |H|)^{1/3}) rate implied by the swap-omniprediction guarantee of Luo et al. (2025). Our main technical contribution is a reduction from swap-agnostic learning to a second-order form of multicalibration, obtained via Blackwell approachability with a Bernstein-style variance correction.
Jul 29, 2026

Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regret

We propose a self-adaptive online learning for control method for tracking unknown target dynamics. The target dynamics can exhibit switching behavior, particularly, a mixture of structured, random, and/or adversarial motion. Such challenging target tracking scenarios arise in applications of dynamic mapping, traffic control, and pursuit evasion, where robots need to track, pursue, or avoid collision with moving landmarks, objects, humans, etc., whose dynamics are unknown. Our method simultaneously learns multiple predictors from scratch, via self-supervised, one-shot, and computationally efficient learning, and adaptively selects the best one to match the observed target behavior. The method enjoys finite-time near-optimality guarantees in expectation, characterized as a function of the learning error of the target dynamics and the frequency that the target dynamics switch. In the absence of both error and switching, the method asymptotically matches the optimal non-causal control policy that knows a priori the target dynamics, i.e., the method enjoys no regret in expectation. In the presence of learning errors and switching, the method degrades gracefully, \eg when there are errors and no switching, the average regret is proportional to the average learning error and switching times. To prove these guarantees, a novel technical approach is required compared to the existing works that employ RFF-based online learning. We validate our method in Crazyflie simulations and hardware experiments, across target trajectories that vary from structured to random to adversarial, in comparison to non-stochastic, kernel-based, and neural-network-based methods for online learning.
Jul 28, 2026

Distributed Constraint Optimization via Online Learning and Iterative Pricing with Application to Large-Scale Satellite Scheduling

Distributed constraint optimization problems (DCOPs) provide a popular framework for distributed decision making under limited communication, but many real-world instances are too large to solve monolithically. We address this challenge from two complementary directions. We revisit the connection between DCOPs and potential games, and adapt modern online learning algorithms for equilibrium finding to DCOPs. We show that these algorithms are competitive with representative incomplete DCOP algorithms. We then turn to decomposition frameworks for large-scale DCOPs, motivated by large-scale decentralized satellite scheduling. We propose a new framework that separates a DCOP into two interacting subproblems: a high-level meta-DCOP for task allocation, and independent local optimization problems for scheduling. To couple the two levels, we develop a novel iterative pricing method that updates the meta-level utilities using feedback from the local optimizers. Combining our online learning methods with our iterative pricing framework, we obtain near-optimal performance on real-world decentralized satellite scheduling problem instances, fulfilling over 99% of observation requests compared with 87% for state-of-the-art baselines.