arXiv subjects

Tongxin Li

Publications and source records attributed to Tongxin Li.

At least 19 recordsLinked to original sources

arXiv2026

Reinforcement Learning with Multi-Step Transition Predictions: A Bellman Theory

Multi-step predictions of future transition realizations can improve reinforcement learning, but their value remains difficult to quantify. Directly including these predictions in the state can lead to exponential state-space growth, making direct dynamic programming computationally expensive. We study discounted finite MDPs under a block-feedback protocol: at the start of each K-period block, the decision maker observes $K$-step probabilistic transition predictions for a subset of actions and adapts decisions to observed states within the block. We show that the optimal value satisfies a Bayesian Bellman equation on the original state space. This representation reveals that predictive information creates value by recursively changing the local order of maximization and expectation in the Bellman expansion. We formalize this effect through a Bellman--Jensen analysis and quantify the effects of prediction horizon, error, action coverage, and within-block feedback. We propose block-feedback Bayesian offline learning with online adaptation (BF--BOLA), a model-based algorithm for learning near-optimal policies, and establish upper and lower sample-complexity bounds that match up to logarithmic factors in the stated regimes. The results show that predictions can reduce transition learning to uncovered rows and that learning a near-optimal policy can require fewer prediction samples than estimating the Bayesian value function.

cs.LG↗

arXiv2026

Near-Optimal Consistency-Robustness Bounds for Non-Clairvoyant Scheduling

We study the problem of characterizing the optimal consistency--robustness tradeoff for single-machine non-clairvoyant scheduling with predicted processing times. For a fixed number of jobs $n$, Wei and Zhang (2020) established a lower bound on the achievable consistency--robustness tradeoff which is known to be tight only in a few restrictive cases, leaving the optimal tradeoff for general $n$ unresolved. A different worst-case-$n$ regime was introduced by Benomar et al. (2025), who applied the former work's construction to show that for $λ\in (0, 1)$, any $(1+λ)$-consistent algorithm must be $1 + Ω(\sqrt{1/λ})$-robust. On the other hand, the best known upper bound gives $(1+λ)$-consistency and $1+O(1/λ)$-robustness, leaving a polynomial gap. In this work, we develop a new lower bound using a multi-stage adversarial construction and a new algorithm that together give a near-optimal characterization of the consistency--robustness tradeoff: for every $n$, our upper bound is within a multiplicative factor $3/2$ of our lower bound, and thus our algorithm is within a multiplicative factor $3/2$ of the online optimal. In particular, our lower bound shows that any $(1+λ)$-consistent algorithm must have robustness at least $1/\sqrtλ$ as $n \to \infty$, while our algorithm achieves robustness at most $\frac{1}{2}+\sqrt{\frac{5}{4}+1/λ}$ for any $n$, matching the lower bound in the leading term as $λ\downarrow 0$; our upper bound also closes the polynomial gap in the worst-case-$n$ regime. We additionally show how our algorithm can be made error-tolerant, preserving the near-optimal consistency-robustness tradeoff while incurring only slightly degraded performance under bounded prediction errors.

cs.DS↗

arXiv2026

The Exact Boundary of Linear Optimality in Witsenhausen's Counterexample

Witsenhausen's counterexample has resisted a closed form solution for decades. However, it has remained unknown whether a mathematically tractable representation exists or not. In this paper, we solve this open problem, showing that the optimal policies are either linear or not tame and characterizing the exact regions where the two properties hold. Moreover, in the linear optimal region, we give an essentially unique closed form solution for the optimal policy, and show that no optimal first-stage policy is definable in any $o$-minimal expansion of the ordered real field in the nonlinear optimal region.

eess.SY↗

arXiv2026

A short open space curve of unit width

In this work, we propose a curve to be a minimum of length among rectifiable, continuous curves of unit width in three-dimensional Euclidean space. We show that a previously conjectured minimizer of that problem is not of unit width, give the numerical derivation of a candidate family of unit width curves, prove that it admits a strict local minimum within that candidate family and that this minimum is of unit width and length $3.905124162243593\ldots$. The curve consists of eight straight segments, two cone geodesics, and three circular helices. Its parameters are specified by a uniquely isolated solution of the joining and stationarity equations. To establish unit width in every direction, we combine analytic estimates with interval arithmetic on a finite covering of the remaining directions. We conjecture that the curve is globally minimizing. We supplement this work with the programs used to identify the candidates, replicate the computer-assisted parts of our proof, as well as a formalization of our proof in Lean.

math.MG↗

arXiv2026

Secure-CUA: Controlling Untrusted Influence in Computer-Use Agents

Computer-use agents (CUAs) perform tasks across applications (such as desktops, mobile apps, and web browsers) by observing graphical interfaces and issuing commands such as clicks and keystrokes. These interfaces combine trusted controls and content with untrusted content needed for legitimate tasks. An adversary controlling this untrusted content can embed instructions or misleading visual cues to change the agent's intended action or redirect its commands to the wrong interface target. We formalize security requirements for both the agent's decisions and their execution through GUI commands. In an ideal execution model, we show that enforcing both requirements at each step protects execution traces. We instantiate this model in Secure-CUA, our system for secure CUA execution. Its key idea is to commit to an explicit per-action program, called an $\textit{action transaction}$, before accessing untrusted content. Each transaction fixes its queries to untrusted content and the permitted uses of their responses. The system masks untrusted regions and evaluates each transaction to produce the next action, using an isolated query model to answer its queries. It then locates the intended interface target using the masked interface. Under the model's assumptions, Secure-CUA is secure by design, while generating a new transaction at each step helps maintain high task utility by adapting to changing interfaces. We evaluate Secure-CUA under benign conditions on 400 WebArena tasks using three frontier models across $5$ seeds, yielding $6,000$ execution traces. Secure-CUA achieves an average task success rate of $53.55\%$, compared with $55.12\%$ for Vanilla-CUA and $13.17\%$ for CaMeL-CUA.

cs.CR↗

arXiv2026

GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection

We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignment on the unit hypersphere. GLASS builds a unified representation space by aligning a structure-aware graph encoder with an instruction-aware text embedding via a multi-slice soft cosine objective. Our framework serializes local, global, and semantic graph properties into a compact Graph Descriptor Prompt (GraphDP), creating a text bridge that enables domain-agnostic anomaly scoring. By enforcing multi-scale consistency through Matryoshka representation slices, the model captures anomalous deviations at multiple levels of granularity. We formulate anomaly detection as density estimation on the aligned hypersphere and introduce Spherical Multi-Modal Scoring (SMS), which instantiates von Mises-Fisher kernel density estimators in both graph and text embedding spaces. This probabilistic formulation recovers angular 1-nearest-neighbor scoring in the high-concentration limit, motivates the practical mean k-nearest-neighbor scorer, and provides a principled fusion of structural and semantic anomaly signals. The shared text embedding space further serves as a cross-domain bridge: by encoding a target domain's GraphDP without target-domain training data, GLASS performs zero-shot anomaly detection, and with only a handful of normal examples, few-shot adaptation via reference-set calibration. For privacy-sensitive deployment, we extend reference-set calibration with a bounded joint graph-text kernel summary that provides graph-record differential privacy while keeping the encoders fixed independently of the private target references. Across twelve benchmarks and three meta-domains, GLASS obtains the best average AUROC and rank compared with recent advanced GLAD baselines and enables effective cross-domain transfer.

cs.LG↗

arXiv2026

Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring

Non-intrusive load monitoring (NILM) estimates appliance-level consumption from a whole-home meter, but appliance-specific models and fixed output inventories make coverage costly to extend. We present FM4NILM (Foundation Model for NILM), a single prompt-programmable model that estimates a requested appliance's power trajectory from aggregate measurements, a natural-language description, and optional activation exemplars. A lightweight cadence-aware transformer is pretrained by masked reconstruction on 645k sequences from seven public corpora spanning 1-60 s sampling intervals, then aligned with appliance requests using observation-masked losses for partially labeled households. A Bernoulli-lognormal decoder separates activity detection from conditional power estimation. On held-out households and time periods from REDD, UK-DALE, and REFIT, one frozen text-prompted model serves twelve appliance-corpus requests, achieving 0.556 event F1, 0.625 AUPRC, and the lowest active-window MAE (251.8 W) among seven appliance-specific baselines. Streaming score aggregation raises event F1 to 0.582 with a 60 s aggregation delay. In a separate category-held-out evaluation, adding ten activation exemplars raises microwave AUPRC from 0.132 to 0.214 without parameter updates. Input-intervention ablations probe the model's dependence on appliance requests and aggregate measurements. These results demonstrate competitive disaggregation with one shared model and support extending appliance coverage through prompts and examples rather than additional specialist networks.

cs.LG↗

arXiv2026

AUSO: Action-Level Unified Skill Optimization from Internalization to Utilization

Skills play different roles as an agent's policy evolves: they should first provide learnable knowledge, then support capability formation, and finally be invoked only when they improve individual decisions. Existing methods rarely model this lifecycle. They either keep skills outside the model, fully internalize them, or select among internalization and utilization objectives through noisy task-level success rates. Such designs fragment training and assign uniform importance to actions within the same trajectory, even though skill guidance may help some decisions while distracting others. To solve these problems, we introduce AUSO (Action-level Unified Skill Optimization), which unifies skill learning and skill use through a progressive, action-aware optimization process. At the beginning of training, AUSO jointly learns from teacher guidance and environmental outcomes, enabling the policy to acquire foundational skills without losing task-oriented feedback. It subsequently emphasizes outcome-based policy optimization to consolidate autonomous problem-solving ability. As the policy matures, AUSO evaluates each sampled action under both skill-conditioned and skill-free contexts. The resulting action-level information signal is coupled with the trajectory outcome advantage, allowing beneficial skill-sensitive actions to receive stronger updates and harmful ones to be suppressed. Therefore, skills gradually transition from an external source of supervision into decision knowledge whose utilization is adapted to its action-level benefit, while reinforcement learning remains the shared backbone across all stages. Experiments on ALFWorld, WebShop, and SearchQA show that AUSO consistently improves agent performance and out-of-distribution generalization over competitive baselines.

cs.AI↗

arXiv2026

Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions

We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice. Our work departs from the typical approach of treating advice as coming from black-box sources by instead considering a setting where additional information about how the advice is generated is available. We prove a first-of-its-kind consistency and robustness tradeoff given Q-value advice under a general MDP model that includes both continuous and discrete state/action spaces. Our results highlight that utilizing Q-value advice enables dynamic pursuit of the better of machine-learned advice and a robust baseline, thus result in near-optimal performance guarantees, which provably improves what can be obtained solely with black-box advice.

cs.LG↗

arXiv2026

World Models in Pieces: Structural Certification for General Agents

In the big-world regime, agents cannot be universally capable and their ability is inevitably specialized across a world model in pieces. Consequently, standard uniform guarantees fail to distinguish between the understanding of critical bottlenecks and irrelevant failures. We first formalize this limitation by proving that general agents are not universal, rendering standard worst-case analysis uninformative. To overcome this, we introduce structural certification, a transition-local framework that maps bounded goal-conditioned performance to entry-wise guarantees on the agent's internal world model. Our main contribution is constructive. We provide algorithms that filter specific transitions using deep compositional goals and prove that a general agent on these goals has a structural world model with a $\mathcal{O}(1/n) + \mathcal{O}(δ)$ error bound. Conversely, this bound is tight in the small-$δ$ regime, whose existence is explicitly guaranteed by our certification. These results enable the certifiable deployment of general agents by localizing the specific transitions where long-horizon planning is reliable.

cs.AI↗

arXiv2026

Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning

Non-Intrusive Load Monitoring (NILM) offers a cost-effective method to obtain fine-grained appliance-level energy consumption in smart homes and building applications. However, the increasing adoption of behind-the-meter (BTM) energy sources such as solar panels and battery storage poses new challenges for conventional NILM methods that rely solely on at-the-meter data. The energy injected from the BTM sources can obscure the power signatures of individual appliances, leading to a significant decrease in NILM performance. To address this challenge, we present DualNILM, a deep multi-task learning framework designed for the dual tasks of appliance state recognition and injected energy identification. Using a Transformer-based architecture that integrates sequence-to-point and sequence-to-sequence strategies, DualNILM effectively captures multiscale temporal dependencies in the aggregate power consumption patterns, allowing for accurate appliance state recognition and energy injection identification. Extensive evaluation on self-collected and synthesized datasets demonstrates that DualNILM maintains an excellent performance for dual tasks in NILM, much outperforming conventional methods. Our work underscores the framework's potential for robust energy disaggregation in modern energy systems with renewable penetration. Synthetic photovoltaic augmented datasets with realistic injection simulation methodology are open-sourced at https://github.com/MathAdventurer/PV-Augmented-NILM-Datasets.

cs.LG↗

arXiv2026

Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners

We study how an agent in a two-player repeated game can effectively utilize potentially imperfect advice when interacting with a no-regret learner. We characterize the advice landscape by introducing a pseudo-metric to quantify the usefulness of an advice instance. We demonstrate the pseudo-metric's applicability through two forms of advice: simulators and payoff matrix predictions. We then show how an optimizing player, equipped with correctness guarantees on the advice, could leverage simulators to compute approximate Stackelberg strategies more efficiently, reducing the interaction complexity traditionally required and illustrating the power of good advice. Finally, we extend our analysis to settings where the advice does not have any guarantee of correctness. We find that, in general, a player cannot simultaneously guarantee near Stackelberg performance when the advice is approximately accurate and a no-regret condition when the advice is inaccurate. We do show, however, that it is possible for an advice-aided player to weakly dominate their utility in some (coarse)-correlated equilibria.

cs.GT↗

arXiv2026

Safety-Critical Contextual Control via Online Riemannian Optimization with World Models

Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner must optimize a task objective using only feasibility samples from a black-box Simulator, conditioned on a context signal $ξ_t$. We develop a sample-based Penalized Predictive Control (PPC) framework grounded in online Riemannian optimization, in which the Simulator compresses the feasibility manifold into a score-based density $\hat{p}(u \mid ξ_t)$ that endows the action space with a Riemannian geometry guiding the Planner's gradient descent. The barrier curvature $κ(ξ_t)$, the minimum curvature of the conditional log-density $-\ln\hat{p}(\cdot\midξ_t)$, governs both convergence rate and safety margin, replacing the Lipschitz constant of the unknown dynamics. Our main result is a contextual safety bound showing that the distance from the true feasibility manifold is controlled by the score estimation error and a ratio that depends on $κ(ξ_t)$, both of which improve with richer context. Simulations on a dynamic navigation task confirm that contextual PPC substantially outperforms marginal and frozen density models, with the advantage growing after environment shifts.

eess.SY↗

arXiv2026

Context-Aware Model Predictive Control for Microgrid Energy Management via LLMs

The optimal operation of modern microgrids, particularly those integrating stochastic renewable generation and battery energy storage system (BESS), relies heavily on load and disturbances forecasting to minimize operational costs. However, in environments with uncertainties in both generation and consumption, traditional numerical forecasting methods often fail to capture generation shifts and event-driven load surges. While contextual information regarding event schedules, system logs, and computational task records is easily obtainable, classic control paradigms lack a formal interface to integrate the unstructured, semantic data into the physical operation loop. This paper addresses this gap by introducing the InstructMPC framework, which utilizes a Large Language Model (LLM) paired with a tunable last layer mapping to translate unstructured operational context into predictive disturbance trajectories for the MPC controller. Unlike conventional forecasting methods, the proposed approach treats the last layer mapping as a tunable component, refined online based on the realized control cost. We establish a theoretical foundation for this closed-loop tuning strategy, proving a regret bound of $O(\sqrt{T \log T})$ for linear systems under a tailored task-aware loss function, together with robustness guarantees against uninformative or noisy textual inputs. The control strategy is experimentally validated on OpenCEM, a real-world microgrid with highly fluctuating generation and consumption. Experimental results demonstrate that the LLM-driven MPC significantly reduces cumulative grid electricity costs compared to classical context-agnostic baselines, validating the efficacy of integrating semantic information directly into physical control loops.

eess.SY↗

arXiv2026

Bridging Natural Language and Microgrid Dynamics: A Context-Aware Simulator and Dataset

Addressing the critical need for intelligent, context-aware energy management in renewable systems, we introduce the OpenCEM Simulator and Dataset: the first open-source digital twin explicitly designed to integrate rich, unstructured contextual information with quantitative renewable energy dynamics. Traditional energy management relies heavily on numerical time series, thereby neglecting the significant predictive power embedded in human-generated context (e.g., event schedules, system logs, user intentions). OpenCEM bridges this gap by offering a unique platform comprising both a meticulously aligned, language-rich dataset from a real-world PV-and-battery microgrid installation and a modular simulator capable of natively processing this multi-modal context. The OpenCEM Simulator provides a high-fidelity environment for developing and validating novel control algorithms and prediction models, particularly those leveraging Large Language Models. We detail its component-based architecture, hybrid data-driven and physics-based modelling capabilities, and demonstrate its utility through practical examples, including context-aware load forecasting and the implementation of online optimal battery charging control strategies. By making this platform publicly available, OpenCEM aims to accelerate research into the next generation of intelligent, sustainable, and truly context-aware energy systems.

eess.SY↗

arXiv2026

Understanding Educators' Perceptions of AI-generated Non-consensual Intimate Imagery

AI-generated non-consensual intimate imagery (AIG-NCII) is an emerging social problem due to the advancement of AI tools. While recent incidents in middle and high schools have highlighted the urgency of this issue, there is limited understanding of what concrete supports schools need to effectively address AIG-NCII. To fill this gap, we conducted an interview study with 20 educators in the U.S. and investigated their attitudes, experiences, and practices related to AIG-NCII. Educators expressed concerns about both students' and their own vulnerability, as AIG-NCII may cause moral decline among students, while educators themselves could become victims. Nevertheless, existing practices in schools are limited, and they lack both training and systematic policies. Challenges such as a lack of resources, unclear legal boundaries, and limited knowledge of AI make implementation difficult. The findings of this paper contribute to interactive educational tool design, curriculum design, and policy-making, especially regarding the need for multi-stakeholder strategies to address issues surrounding AIG-NCII.

cs.HC↗

arXiv2026

Quantum-Enabled Probabilistic Optimal Power Flow with Built-in Differential Privacy

Quantum computing has been regarded as a promising approach to accelerate power system optimization. However, challenges such as limited qubits and inherent noise hinder their widespread adoption in power systems. In this paper, we propose a qubit-efficient framework for solving a crucial power system optimization problem, the probabilistic optimal power flow (POPF). We demonstrate that quantum noise, traditionally viewed as a drawback, can in fact be leveraged to provide a built-in differential privacy (DP) guarantee. Specifically, we first linearize POPF into a multi-parametric linear program (MP-LP) with renewable uncertainties being the parameters. This decomposes the parameter space into critical regions with precomputed solution maps. Second, a variational quantum circuit (VQC) classifies the critical region based on each uncertainty realization and then recovers the final solution. In this way, the required qubits scale with the uncertain parameters instead of the network size, with only 5 qubits versus 600+ for direct quantum OPF in a 69-bus system. Moreover, we prove the depolarizing noise of VQC provides DP guarantees and characterize the privacy-cost tradeoff. Case studies validate the proposed VQC achieves 2.1$\times$ smaller privacy budgets compared to its classical counterpart. At matched privacy levels, the VQC also maintains lower infeasibility and prediction error.

math.OC↗

arXiv2026

Quantum Learning and Estimation for Coordinated Operation between Distribution Networks and Energy Communities

Price signals from distribution networks (DNs) guide energy communities (ECs) in adjusting their energy usage, enabling effective coordination for reliable power system operation. However, this coordinated operation faces significant challenges due to the limited availability of ECs' internal information (i.e., only the aggregated energy usage of ECs is available to DNs), and the high computational burden of accounting for uncertainties and the associated risks through numerous scenarios. To address these challenges, we propose a quantum learning and estimation approach to enhance coordinated operation between DNs and ECs. Specifically, by leveraging advanced quantum properties such as quantum superposition and entanglement, we develop a hybrid quantum temporal convolutional network-long short-term memory (Q-TCN-LSTM) model to establish an end-to-end mapping between ECs' responses and the price incentives from DNs. Moreover, we develop a quantum estimation method based on quantum amplitude estimation (QAE) and two phase-rotation circuits to significantly accelerate the optimization process under numerous uncertainty scenarios. Numerical experiments demonstrate that, compared to classical neural networks, the proposed Q-TCN-LSTM model improves the mapping accuracy by 69.2\% while reducing the model size by 99.75\%. Compared to classical Monte Carlo simulation, QAE achieves comparable accuracy with a substantial reduction in computational resources. In addition, the estimated computation time for quantum learning and estimation on ideal quantum devices is over 90\% shorter than that of traditional methods.

math.OC↗