Searcharxiv⌕ Search

arXiv subjects

Yuanyuan Shi

Publications and source records attributed to Yuanyuan Shi.

At least 19 recordsLinked to original sources
arXiv2026

Evolving Memory, Learning to Meta-Control: Test-Time Adaptation for Experience-augmented LLM Agents

Self-evolving agents accumulate experience from task streams, but existing frameworks typically rely on fixed pipelines to retrieve and utilize this experience, neglecting when and how to deploy it. We introduce Online Meta-Control of Experience (OMCE), a framework that updates experience memory and learns a meta-control policy from task feedback during test-time adaptation. OMCE employs a lightweight contextual-bandit meta-controller that uses compact retrieval signals to select among four cognitive actions: DIRECT, EPISODE, GUIDE, and DISTILL. This routing mechanism operationalizes three coupled decisions: whether to invoke experience, which memory format to utilize, and when to consolidate new guidance. OMCE evolves online, leveraging task feedback to update the memory bank and refine the routing policy via contextual bandit updates. Experiments on four online adaptation benchmarks across four backbones show that OMCE improves first-attempt success by up to 20.5 percentage points over the strongest compared baseline, while reducing per-task token use by a factor of 5.7 to 62.5 relative to ACE with GPT-5.2. Controlled ablations further support the benefits of learned routing and continued routing policy adaptation.

cs.LG↗
arXiv2026

Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this paper, we propose using Low-Rank Adaptation (LoRA) as a structural regularizer for critic learning from scratch. Our approach freezes randomly initialized base matrices and optimizes only the corresponding low-rank adapters, thereby constraining the learned weight changes to low-rank residuals. We evaluate our method on state-based continuous-control tasks, using SAC with SimbaV2 and BRC on DMC-Hard, and FastTD3 with its SimbaV2 variant on IsaacLab. Empirically, LoRA reduces critic loss during training and improves overall policy performance, achieving the best or competitive results on most tasks. Extensive experiments demonstrate that our low-rank updates provide a simple and effective form of structural regularization for critic learning in off-policy RL.

cs.LG↗
arXiv2026

When Agents Fail: Model or Harness--Who's to Blame?

LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior. We argue that harnesses should therefore be evaluated through their interactions with underlying models. We develop a framework combining five complementary measures: (i) Valid Completion Rate (VCR), how reliably agents finish normally and deliver evaluable results, irrespective of task correctness; (ii) Model-Harness Fit, how well a harness supports task achievement through valid completion for a given model; (iii) Cross-Model Fit, a harness's overall suitability across evaluated models; (iv) Interaction Residuals, pairing-specific execution strengths and weaknesses hidden by component-level summaries; and (v) Token Load, the token demands of agent execution, including failed attempts. We evaluate four general-purpose harnesses (OpenCode, Codex CLI, Pi CLI, and DeepAgents) with four core models, plus two fixed native model-harness systems, on six benchmarks covering context management, tool use, long-context planning, multimodal interaction, and artifact handoff. Including native references and stress conditions, 111 evaluation settings yield 52,168 trajectories. Harness rankings vary across models and benchmarks; task performance and valid completion can favor different pairings, and similar task scores can accompany distinct execution profiles. OpenCode ranks first in cross-model performance, while DeepSeek V4 Flash Preview maintains consistently high Mean VCR across harnesses on the shared four-benchmark panel. These findings support evaluating model-harness interactions, training transferable harness-use capabilities in models, and harness designs adapted to the model and task.

cs.AI↗
arXiv2026

Carbon-Aware Joint Resource and Energy Scheduling for Cellular Base Stations

Decarbonizing cellular networks requires coordinating communication-resource and battery operation with time-varying electricity prices and carbon intensity. We jointly optimize base station and battery operation under a carbon-adjusted electricity price and traffic-demand constraints, and solve the mixed-integer nonconvex problem through a two-stage decomposition exact under a minimum-power rule. Using California price and carbon-intensity data, we show that carbon-aware scheduling reduces emissions most when low-price and low-carbon periods are misaligned. Above a carbon price of roughly 100-300 USD/ton, battery operation shifts from cost-driven to carbon-driven, cutting emissions by up to 57.8% relative to a cost-only schedule.

eess.SP↗
arXiv2026

Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution

Particle-in-cell (PIC) simulation is indispensable for modeling beam dynamics in particle accelerators, but its computational cost limits many-query workflows, such as configuration exploration, virtual diagnostics, and controller design. We introduce GLOBE, a physics-constrained Generative Latent Operator for Beam Evolution, modeling the nonlinear, control-dependent, multiscale evolution of 3D beam--field dynamics covering $10^7$ spatial cells. GLOBE compresses beam--field states into a compact latent space and factors their evolution into two components. A control-conditioned neural operator learns the dominant dynamics, while an amplitude-normalized generative model captures the residual distribution, recovering fine-scale structures and conditional variations. GLOBE enforces field constraints by regime-specific, parameter-free operators: a Poisson solve reconstructs the electric field in the electrostatic regime, and a spectral projection imposes Gauss's law and a divergence-free magnetic field in the electromagnetic regime. On two high-resolution 3D particle-accelerator benchmarks, bunched-beam transport and plasma-wakefield acceleration, GLOBE lowers relative-$L_2$ error by 9\% and 13\%, low-frequency spectral error by 69\% and 51\%, and mid-frequency spectral error by 54\% and 20\% relative to the strongest baseline (DPOT), satisfies field constraints, and reduces hours of PIC simulation to a minute per rollout.

physics.acc-ph↗
arXiv2026

Rapid Fredholm stabilization of the Kuramoto--Sivashinsky equation with unrestricted, spatially-varying anti-diffusion

We develop the first feedback design for rapid stabilization of the Kuramoto--Sivashinsky equation with a spatially varying anti-diffusion coefficient. For constant coefficients, the single-input Fredholm design of Coron and Lü (2015) excludes a discrete set of values at which repeated unstable eigenvalues cause a loss of controllability. We overcome this obstruction by introducing a second boundary input and assigning the two inputs distinct roles. The key idea, inspired by Heymann's Lemma, is to use the boundary value $u(0,t)$ entirely for a pre-feedback that renders the modified plant controllable through the curvature input $u_{xx}(0,t)$. The latter input then stabilizes the plant through a Fredholm backstepping transformation. We show that two inputs suffice for controllability and are necessary when the plant has an unstable double eigenvalue. However, the Fredholm kernel still must be approximated for implementation. Hence, to enable kernel and gain approximation, we prove continuity of the coefficient-to-gain design map on compact admissible design classes. Unlike Volterra-based continuity proofs using successive approximations, our proof uses the modal representation to control the spectral data, the inverse coefficient system, and the tails of the kernel and gain series. This yields a single neural operator approximation of the gain to any prescribed $L^2$ accuracy across the class. Finally, we establish rapid local stabilization of the nonlinear closed-loop system under both the exact gains and sufficiently accurate approximations. We conclude with numerical results that illustrate prescribed decay rates and the computational cost of the approximations. In particular, we train a Fourier neural operator that achieves typical relative gain errors of approximately $0.1\%$ and stabilizes all held-out cases tested, including a plant with an unstable double eigenvalue.

eess.SY↗
arXiv2026

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectories extend. While in practice, many queries do not require the capabilities of the largest available model, and routinely directing such queries to a high-capability model can introduce unnecessary, considerable computation and energy consumption. In this paper, we investigate whether adaptive routing across a heterogeneous pool of LLMs can reduce this energy burden without substantially compromising task performance. We design a language-model-based router that reads in each query and selects an answer model from a fixed candidate pool. The candidate models are first profiled through an offline tournament that records their correctness, latency, power, and GPU energy for each query. Using these measurements, the router is trained through supervised fine-tuning followed by group relative policy optimization (GRPO) with the tailored paradigms. Results demonstrate that learned routing can selectively allocate expensive model capacity based on query context and improve the accuracy-energy tradeoff in multi-LLM serving. Across seven benchmark tasks, we also observe a sharp accuracy-energy phase transition among routers, providing practical insights into improving energy efficiency while maintaining LLM performance.

cs.PF↗
arXiv2026

Recursive Self-Improvement LLM Agents for Inverter Dynamic Model Identification

This is a position paper. We demonstrate that recursive self-improvement (RSI) large language model (LLM) agents are a natural search engine for dynamic model identification of inverter-based resources (IBRs) whose internal controls are often proprietary and hidden from grid operators. White-box models provide physical transparency but require vendor disclosure; black-box models avoid this requirement but sacrifice interpretability; and existing grey-box approaches, including sparse and symbolic regression, are poorly suited to discovering feedback control architectures or incorporating control-engineering priors. Our position is that this gap can be alleviated by (1) restricting the search space to a typed vocabulary of standard control modules, including PI controllers, phase-locked loops (PLLs), low-pass filters, etc., composed under block-diagram grammar rules, and (2) using an RSI LLM agent to perform program search over candidate block-diagram models, guided by measured frequency-domain admittance data at the point of common coupling (PCC), while fitting the free parameters of each candidate by nonlinear least squares. We instantiate this position by adapting ThetaEvolve, an open-source program-evolution framework supporting in-context evolution and test-time learning, to inverter model discovery. In a proof-of-concept study on a grid-following (GFL) inverter benchmark, the RSI loop reduces the normalized root mean square error (NRMSE) of a naive open-loop model from 0.470 to 0.0435 and identifies a 15-module closed-loop structure that closely resembles the hidden ground-truth GFL controller.

eess.SY↗
arXiv2026

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend heavily on ground-truth supervision (e.g., verifiable reward). Such annotations are costly to obtain and become increasingly scarce as reasoning capabilities advance beyond what humans can reliably evaluate. Self-rewarding RL reduces this dependence by enabling models to derive reward signals from their own completions. However, training solely on self-generated feedback can reinforce existing biases and suboptimal behaviors, reduce response diversity, and ultimately lead to homogenized responses and training collapse. In this work, we show that unsupervised reasoning can emerge through cooperative multi-agent training. We introduce Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers. We further show that increasing cohort diversity, through heterogeneous model families, sizes, and rephrased training samples, reduces the correlated errors that drive self-reinforcing feedback loops. This diversity consistently improves reasoning performance, maintains behavioral diversity, and mitigates training collapse. Across text-only and multimodal domains, Co-RL consistently outperforms the base models and prior label-free approaches, while matching or surpassing supervised methods, without access to any ground-truth labels. Concretely, Co-RL yields average gains of 3.0-8.6% across seven text-only benchmarks for LLMs and 2.3-7.2% across four multimodal benchmarks for VLMs. Code is available at https://github.com/DrStranded/Co-RL.

cs.LG↗
arXiv2026

Power Estimation and Optimal Work-Charging Scheduling of Construction Electric Vehicles via Mobile Charging Stations

Construction electric vehicles (CEVs) are a promising clean alternative to diesel-powered construction equipment, but their adoption is constrained by sparse onsite charging infrastructure, limited CEV mobility, and insufficient understanding of their power consumption. We address these gaps through a field-data-driven framework coupling CEV power estimation with mobile-charging-aware work scheduling. First, using a real-world construction demonstration at the University of California, San Diego, we develop and validate a per-subactivity power estimation model for a compact electric excavator. Manually labeled video is synchronized with coarse battery state-of-charge (SOC) telematics, and constrained nonnegative least squares is used to recover each subactivity's average power consumption. The model predicts held-out test data within $17\%$ normalized mean absolute error (NMAE), and the accompanying dataset is released publicly. Second, leveraging the subactivity power estimates, we formulate a mixed-integer program that jointly optimizes CEV work and charging schedules together with the location, timing, and charging/discharging of mobile charging stations (MCSs) serving the CEVs. The optimization accounts for energy and demand charges, carbon emissions, unmet work penalties, MCS travel, and the physical and operational constraints of the CEVs and MCSs. Across realistic scenarios drawn from the demonstration, the proposed co-optimization attains the lowest operating cost in every case, being $7$--$96\%$ below the best-performing baseline, while solving most instances to proven optimality within an hour. Dataset and scripts are available at https://github.com/ghosh-avik/CEV-MCS-Power-Estimation-and-Joint-Scheduling.

eess.SY↗
arXiv2026

LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications

Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains. In smart grids, recent work applies agentic schemes to forecasting, optimization, and control, wrapping trusted solvers behind language interfaces and orchestrating multi-step workflows. The literature lacks a unified approach to designing and evaluating such systems. LLMs can produce numerically plausible yet physically infeasible outputs, evaluation protocols vary across tasks, and the boundary between what the model should and should not compute is implicit. This paper presents a solver-grounded design principle: a numerical result is reported only when it originates from a trusted tool and passes explicit verification. We review the building blocks of LLM and agentic AI systems for power systems: prompting strategies and agentic architectures. We instantiate the principle in four case studies: wind power forecasting, EV charging scheduling, power flow analysis, and contingency diagnosis, each comparing an LLM-only baseline against its solver-grounded counterpart on identical data and metrics. EVAgent reproduces the CVXPY optimum while reducing LLM-only unmet energy by 7.5-9.5x, and GridDebugAgent repairs 17/39 contingency cases while reducing total violations by 52.3%. We propose a four-group evaluation framework spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency. A consistent division of labor emerges: the agentic system reliably orchestrates, retrieves, and explains, while trusted tools compute and a verification gate decides what is reported.

eess.SY↗
arXiv2026

Control-Oriented System Identification: Classical, Learning, and Physics-Informed Approaches

We survey classical, machine learning, and data-driven system identification approaches to learn control-relevant and physics-informed models of dynamical systems. Recently, machine learning approaches have enabled system identification from noisy, high-dimensional, and complex data. However, their utility is limited by their ability to provide provable guarantees on control-relevant properties. Meanwhile, control theory has identified several properties that are useful in analysis and control synthesis, such as dissipativity, monotonicity, energy conservation, and symmetry-preserving structures. We posit that merging system identification with such control-relevant or physics-informed properties can provide useful inductive bias, enhance explainability, enable control synthesis with provable guarantees, and improve sample complexity. We formulate system identification as an optimization problem where control-relevant properties can be enforced through direct parameterization (constraining the model structure to satisfy a desired property by construction), soft constraints (encouraging control-relevant properties through regularization or penalty terms), and hard constraints (imposing control-relevant properties as constraints in the optimization problem). Through this lens, we survey methods to learn physics-informed and control-relevant models spanning classical linear and nonlinear system identification, machine learning approaches, and direct identification through data-driven and behavioral representations. We also provide several expository examples that are accompanied by code and brief tutorials on a public Github repository. We also describe challenging directions for future research, including identification in networked, switched, and time-varying systems, experiment design, and bridging the gaps between data-driven, learning-based, and control-oriented approaches.

eess.SY↗
arXiv2026

RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning

On-policy Reinforcement Learning (RL) remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy, and policy updates must be conservative. In this paper, we revisit actor policy representation as a first-class design choice for on-policy RL. We study discretized categorical actors, which represent each action dimension as a distribution over discrete bins and induce a policy objective analogous to classification cross-entropy loss. Building on architectural advances from supervised learning, we further pair discretized categorical actors with regularized networks, yielding RN-D. Across diverse continuous-control benchmarks, we show that simply replacing the standard Gaussian actor with our proposed actor substantially improves performance, achieving state-of-the-art results within on-policy RL. We release our code at https://github.com/alwaysbyx/RND-RL.

cs.LG↗
arXiv2026

ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an inference-scaling framework for structured outputs that combines fine-grained beam search with \textbf{ToolPRM}, a process reward model scoring each intra-call decision (function name and argument filling). We build the first fine-grained intra-call supervision dataset via function masking, rollout collection, and step-level annotation. ToolPRM outperforms outcome and coarse-grained reward models in predictive accuracy and yields consistent test-time gains on multiple function-calling benchmarks. We further show that structured generation follows ``\textbf{explore more but retain less}'', since early JSON errors are unrecoverable.

cs.AI↗
arXiv2026

Nonvolatile single-ion memory with picosecond switching

The rapid development of artificial intelligence (AI), Internet of Things (IoT), and edge computing applications has posed severe challenges to conventional memory technologies in terms of density, speed, and energy consumption. Herein, a single-ion transport mechanism is proposed to achieve picosecond (ps) switching capability. For monolayer hexagonal boron nitride (h-BN) with single-atom vacancy defects, first-principles calculations reveal that single-ion penetration across the BN plane dominates the resistive switching. The trapping and release of a single ion correspond to different states of the memory device for one bit of information. Experimentally fabricated single-ion memory exhibits nonvolatile resistive switching with ultra-fast switching speed of 20 ps and ultra-low energy consumption of 310 aJ/bit. This high performance is attributed to the extremely short distance for the single ion to travel through. Such devices pave the way for the realization of high-performance nonvolatile memory with ultra-fast speed, ultra-low energy consumption, and high storage density, that is called the "Unified Memory" long desired by the whole industry.

physics.app-ph↗
arXiv2026

Predictor-Based Output-Feedback Control of Linear Systems with Time-Varying Input and Measurement Delays via Neural-Approximated Prediction Horizons

Due to simplicity and strong stability guarantees, predictor feedback methods have stood as a popular approach for time delay systems since the 1950s. For time-varying delays, however, implementation requires computing a prediction horizon defined by the inverse of the delay function, which is rarely available in closed form and must be approximated. In this work, we formulate the inverse delay mapping as an operator learning problem and study predictor feedback under approximation of the prediction horizon. We propose two approaches: (i) a numerical method based on time integration of an equivalent ODE, and (ii) a data-driven method using neural operators to learn the inverse mapping. We show that both approaches achieve arbitrary approximation accuracy over compact sets, with complementary trade-offs in computational cost and scalability. Building on these approximations, we then develop an output-feedback predictor design for systems with delays in both the input and the measurement. We prove that the resulting closed-loop system is globally exponentially stable when the prediction horizon is approximated with sufficiently small error. Lastly, numerical experiments validate the proposed methods and illustrate their trade-offs between accuracy and computational efficiency.

eess.SY↗
arXiv2026

Sampling-Horizon Neural Operator Predictors for Nonlinear Control under Delayed Inputs

Modern control systems frequently operate under input delays and sampled state measurements. A common delay-compensation strategy is predictor feedback; however, practical implementations require solving an implicit ODE online, resulting in intractable computational cost. Moreover, predictor formulations typically assume continuously available state measurements, whereas in practice measurements may be sampled, irregular, or temporarily missing due to hardware faults. In this work, we develop two neural-operator predictor-feedback designs for nonlinear systems with delayed inputs and sampled measurements. In the first design, we introduce a sampling-horizon prediction operator that maps the current measurement and input history to the predicted state trajectory over the next sampling interval. In the second design, the neural operator approximates only the delay-compensating predictor, which is then composed with the closed-loop flow between measurements. The first approach requires uniform sampling but yields residual bounds that scale directly with the operator approximation error. In contrast, the second accommodates non-uniform, but bounded sampling schedules at the cost of amplified approximation error, revealing a practical tradeoff between sampling flexibility and approximation sensitivity for the control engineer. For both schemes, we establish semi-global practical stability with explicit neural operator error-dependent bounds. Numerical experiments on a 6-link nonlinear robotic manipulator demonstrate accurate tracking and substantial computational speedup of 25$\times$ over a baseline approach.

eess.SY↗
arXiv2026

LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts

Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most existing approaches rely on conventional TopK routing, which requires careful hyperparameter tuning and assigns a fixed number of experts to each token. In this work, we propose LD-MoLE, a Learnable Dynamic routing mechanism for Mixture of LoRA Experts that enables adaptive, token-dependent, and layer-wise expert allocation. Our method replaces the non-differentiable TopK selection with a differentiable routing function and a closed-form solution. Moreover, our design allows the model to adaptively determine the number of experts to activate for each token at different layers. In addition, we introduce an analytical sparsity control objective to regularize the number of activated experts. Extensive experiments on the Qwen3-1.7B and Llama-3.2-3B models show that LD-MoLE achieves the highest average scores compared to state-of-the-art baselines, across a diverse set of benchmarks. Our method not only achieves superior performance, but also demonstrates the ability to learn token-dependent and layer-wise expert allocation.

cs.CL↗