arXiv subjects

Jingyi Zhu

Publications and source records attributed to Jingyi Zhu.

14 recordsLinked to original sources

arXiv2026

PRAXIS: Case-distilled and code-verified AI agents for biological research

Large language models are moving scientific research from text assistance toward agentic workflows, yet biological research requires strong object validation, methodological suitability, reproducibility, and auditability. Prompt engineering, general RAG, or tool use alone cannot reliably produce domain-specific scientific judgment. Here, we present PRAXIS, a verifiable biological research agent framework driven by literature learning and case distillation. PRAXIS converts research experience, failure boundaries, domain rules, and executable procedures into structured long-term memory. By coordinating successful cases, negative cases, rules, and skills, PRAXIS supports problem definition, object validation, method selection, workflow execution, result interpretation, and review feedback across diverse biocomputational tasks. We instantiated PRAXIS as an agent suite for biomedical computing and evaluated it through object validation, case retrieval, memory ablation, public benchmarks, and cross-agent workflows. The results show that case-based learning improves method selection, error suppression, and workflow organization in complex biological research tasks. Rather than replacing scientists, PRAXIS provides a general pathway for transforming research experience into executable, auditable, and transferable agent capabilities.

q-bio.QM↗

arXiv2026

MDAgent: A Multi-Agent Framework for End-to-End Molecular Dynamics Research

Molecular dynamics (MD) simulation is a powerful tool for studying biomolecular structural changes, molecular recognition, transmembrane transport, and functional mechanisms. However, its practical bottleneck lies not only in software operation or parameter setup, but in translating experimental questions into executable, interpretable, and reviewable computational workflows. Here, we present MDAgent, a multi-agent system for end-to-end molecular dynamics research. The system integrates problem understanding, literature-guided strategy design, simulation execution, trajectory analysis, mechanistic interpretation, and quality supervision into a unified workflow, enabling agents not only to run simulations but also to generate research-oriented computational plans and analytical reports. We further introduce a case-based learning mechanism based on Skill and Memory, which stores reusable knowledge from prior tasks, including parameter choices, operational rules, analytical logic, and problem-solving pathways, thereby supporting cross-task transfer without retraining the underlying model. Across multiple representative molecular simulation tasks, MDAgent achieved stable end-to-end performance with improved strategic adaptability, interpretability, and generalization. In an independent complex task involving conformational transitions of TMEM16F and XKR8, the system successfully completed system design, simulation, and mechanistic analysis for large membrane proteins. These results show that combining multi-agent collaboration with case-based learning can transform MD agents from workflow automation tools into scientific question-oriented computational research systems, providing a scalable framework for AI-driven automated research.

q-bio.QM↗

arXiv2026

Transferable Expertise for Autonomous Agents via Real-World Case-Based Learning

LLM-based autonomous agents perform well on general reasoning tasks but still struggle to reliably use task structure, key constraints, and prior experience in complex real-world settings. We propose a case-based learning framework that converts experience from past tasks into reusable knowledge assets, allowing agents to transfer prior case experience to new tasks and perform more structured analysis. Unlike methods based mainly on pretrained knowledge or static prompts, our framework emphasizes extracting and reusing task-relevant knowledge, analytical prompts, and operational skills from real cases. We evaluate the method on a unified benchmark of six complex task categories and compare it with Zero-Shot, Few-Shot, Checklist Prompt, and Rule Memory baselines. Results show that our method achieves consistently strong performance across all tasks and matches or outperforms the best baseline in every case, with especially clear gains on more complex tasks. Further analysis shows that the advantage of case-based learning increases with task complexity, and that practical knowledge acquired by one agent can be reused by others. These findings suggest that case-based learning offers a promising path for building professional agents for real-world work.

cs.AI↗

arXiv2025

Understanding the Ability of LLMs to Handle Character-Level Perturbation

This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three types of character-level perturbations including introducing numerous typos within words, shuffling the characters in each word, and inserting a large number of invisible characters into the text. Surprisingly, even under severe perturbation, such as shuffling nearly all words character-wise to produce text that is almost unreadable to humans, or inserting invisible characters which are several times more than the visible ones as noise, many LLMs still maintain notable performance. We explore the underlying causes of this robustness and find that LLMs exhibit remarkable resilience to chaotic segmentation and fragmented tokenization. Furthermore, we examine the mechanisms by which LLMs remove perturbations to correctly comprehend text, including both implicit and explicit mechanisms for character-level perturbation. We hope that our findings on the low-level robustness of LLMs will unveil their inherent architectural strengths, reveal the potential risks of their misuse, and inform the reliable deployment of LLMs across diverse application scenarios.

cs.CL↗

arXiv2022

Room-temperature coherent optical manipulation of single-hole spins in solution-grown perovskite quantum dots

Manipulation of solid-state spin coherence is an important paradigm for quantum information processing. Current systems either operate at very low temperatures or are difficult to scale-up. Developing low-cost, scalable materials whose spins can be coherently manipulated at room temperature is thus highly-attractive for a sustainable future of quantum information science. Here we report ambient-condition all-optical initialization, manipulation and readout of single-hole spins in an ensemble of solution-grown CsPbBr3 perovskite QDs. Single-hole spins are obtained by sub-picosecond electron scavenging following a circularly-polarized femtosecond-pulse excitation. A transversal magnetic field induces spin precession, and a second off-resonance femtosecond-pulse coherently rotates hole spins via strong light-matter interaction. These operations accomplish nearly complete quantum-state control of single-hole spins at room temperature.

cond-mat.mes-hall↗

arXiv2022

Excitonic Bloch-Siegert shift in CsPbI3 perovskite quantum dots

Coherent interaction between matter and periodic light field induces both optical Stark effect (OSE) and Bloch-Siegert shift (BSS). Observing the BSS has been historically challenging, not only because it is weak but it is often accompanied by a much stronger OSE. Herein, by controlling the light helicity, we can largely restrict the OSE and BSS to different spin-transitions in CsPbI3 perovskite quantum dots, achieving room-temperature BSS as strong as 4 meV with near-infrared pulses. The ratio between the BSS and OSE magnitudes is however systematically higher than the prediction by the non-interacting, quasi-particle picture. With a model that explicitly accounts for excitonic effects, we quantitatively reproduce the experimental observations. This model depicts a unified physical picture of the interplay between the OSE, biexcitonic OSE and BSS in low-dimensional materials displaying strong many-body interactions, forming the basis for the implementation of these effects to information processing, optical modulation and Floquet engineering.

cond-mat.mes-hall↗

arXiv2021

Unraveling the Excitonic Transition and Associated Dynamics in Confined Long Linear Carbon-chains with Time-Resolved Resonance Raman Scattering

Long linear carbon-chains have been attracting intense interest arising from the remarkable properties predicted and their potential applications in future nanotechnology. Here we comprehensively interrogate the excitonic transitions and the associated relaxation dynamics of nanotube confined long linear carbon-chains by using steady state and time-resolved Raman spectroscopies. The exciton relaxation dynamics on the confined carbon-chains occurs on a hundreds of picoseconds timescale, in strong contrast to the host dynamics that occurs on a few picosecond timescale. A prominent time-resolved Raman response is observed over a broad energy range extending from 1.2 to 2.8 eV, which includes the strong Raman resonance region around 2.2 eV. Evidence for a strong coupling between the chain and the nanotube host is found from the dynamics at high excitation energies which provides a clear evidence for an efficient energy transfer from the host carbon nanotube to the chain. Our experimental study presents the first unique characterization of the long linear carbon-chain exciton dynamics, providing indispensable knowledge for the understanding of the interactions between different carbon allotropes.

cond-mat.mtrl-sci↗

arXiv2021

Hessian Estimation via Stein's Identity in Black-Box Problems

When the available information is noisy zeroth-order (ZO) oracle, stochastic approximation methods are popular for estimating the root of the multivariate gradient equation. Inspired by the Stein's identity, this work establishes a novel Hessian approximation scheme. We compare it alongside with second-order simultaneous perturbation stochastic approximation (2SPSA). On the basis of the almost sure convergence and the same convergence rate, 2SPSA requires four ZO queries, while ours requires three ZO queries. Moreover, 2SPSA requires two statistically independent perturbations and two differencing stepsizes, while ours requires generating one perturbation vector only and tuning one differencing stepsize only. Besides, the weighting mechanism for the Hessian estimate is generalized and the smoothness restriction on the loss function is relaxed compared to 2SPSA. Finally, we present numerical support for the reduced per-iteration ZO query complexity.

math.OC↗

arXiv2020

Hessian Inverse Approximation as Covariance for Random Perturbation in Black-Box Problems

In stochastic optimization problems using noisy zeroth-order (ZO) oracles only, the randomized counterpart of the Kiefer-Wolfowitz-type method is widely used to estimate the gradient. Existing algorithms generate randomized perturbation from a zero-mean and unit-covariance distribution. In contrast, this work considers the generalization where the perturbations have a possibly non-identity covariance constructed from the history of the ZO queries. We propose to feed the second-order approximation into the covariance matrix of the random perturbation, so it is dubbed as Hessian-aided random perturbation (HARP). HARP collects four zeroth-order queries per iteration to form approximations for both the gradient and the Hessian. We show the convergence (in an almost surely sense) and derive the convergence rate for HARP under mild assumptions. We demonstrate, with theoretical guarantees and numerical experiments, that HARP is less sensitive to ill-conditioning and more query-efficient than other gradient approximation schemes whose random perturbation has an identity covariance.

math.OC↗

arXiv2020

Error Bounds and Applications for Stochastic Approximation with Non-Decaying Gain

This work analyzes the stochastic approximation algorithm with non-decaying gains as applied in time-varying problems. The setting is to minimize a sequence of scalar-valued loss functions $f_k(\cdot)$ at sampling times $τ_k$ or to locate the root of a sequence of vector-valued functions $g_k(\cdot)$ at $τ_k$ with respect to a parameter $θ\in R^p$. The available information is the noise-corrupted observation(s) of either $f_k(\cdot)$ or $g_k(\cdot)$ evaluated at one or two design points only. Given the time-varying stochastic approximation setup, we apply stochastic approximation algorithms with non-decaying gains, so that the recursive estimate denoted as $\hatθ_k$ can maintain its momentum in tracking the time-varying optimum denoted as $θ_k^*$. Chapter 3 provides a bound for the root-mean-squared error $ \sqrt{E(\|\hatθ_k-θ_k^*\|^2})$. Overall, the bounds are applicable under a mild assumption on the time-varying drift and a modest restriction on the observation noise and the bias term. After establishing the tracking capability in Chapter 3, we also discuss the concentration behavior of $\hatθ_k $ in Chapter 4. The weak convergence limit of the continuous interpolation of $\hatθ_k$ is shown to follow the trajectory of a non-autonomous ordinary differential equation. Both Chapter 3 and Chapter 4 are probabilistic arguments and may not provide much guidance on the gain-tuning strategies useful for one single experiment run. Therefore, Chapter 5 discusses a data-dependent gain-tuning strategy based on estimating the Hessian information and the noise level. Overall, this work answers the questions "what is the estimate for the dynamical system $θ_k^*$" and "how much we can trust $\hatθ_k $ as an estimate for $θ_k^*$."

math.OC↗

arXiv2019

Excitonic Transport and Intervalley Scattering in Exfoliated MoSe2 Monolayer Revealed by Four-Wave-Mixing Transient Grating Spectroscopy

Exciton intervalley scattering, annihilation and relaxation dynamics, and diffusive transport in a monolayer transition metal dichalcogenides are central to the functionality of devices based on them. This motivated us to investigate these properties in exfoliated high-quality monolayer MoSe2 using heterodyned nonlinear four-wave-mixing transient grating spectroscopy. While free exciton excitations are found to be long-lived (~230 ps), an extremely fast intervalley scattering ( less than 120 fs) is observed leading to a negligible valley polarization, consistent with steady state photoluminescence measurements. The exciton population decay shows an appreciable contribution from exciton-exciton annihilation reactions with an annihilation constant of ~ 0.01 cm2s-1, which in addition leads to an extra contribution to the transient grating response. The underlying excitonic dynamics were numerically modeled by including exciton-exciton annihilation, also in the diffusion equation, which allows extraction of the diffusion constant, D ~1.4 cm2s-1. Our results provide a method that allows for the disentanglement of the intricate dynamics involving many-body annihilation processes and a detailed characterization of the excitonic properties of monolayer MoSe2

cond-mat.mes-hall↗

arXiv2019

Incoherent phonon population and exciton-exciton annihilation in monolayer WS2 revealed by time-resolved spontaneous Raman scattering

Atomically thin layer transition metal dichalcogenides have been intensively investigated for their rich optical properties and potential applications in nano-electronics. In this work, we study the incoherent optical phonon and exciton population dynamics in monolayer WS2 by time-resolved spontaneous Raman scattering spectroscopy. Upon excitation of the exciton transition, both the Stokes and anti-Stokes optical phonon scattering strength exhibit a large reduction. Based on the detailed balance, the optical phonon population is retrieved, which shows an instant build-up and a relaxation lifetime of around 4 ps at an exciton density E12 cm-2. The corresponding optical phonon temperature rises by 25 K, eventually, after some 10s of picoseconds, leading to a lattice heating by only around 3 K. The exciton relaxation dynamics extracted from the transient vibrational Raman response shows a strong excitation density dependence, signaling an important bi-molecular contribution to the decay. The exciton relaxation rate is found to be (70 ps)-1 and exciton-exciton annihilation rate 0.1 cm2s-1. These results provide valuable insight into the thermal dynamics after optical excitation and enhance the understanding of the fundamental exciton dynamics in two-dimensional transition metal materials.

cond-mat.mtrl-sci↗

arXiv2019

Efficient Implementation of Second-Order Stochastic Approximation Algorithms in High-Dimensional Problems

Stochastic approximation (SA) algorithms have been widely applied in minimization problems when the loss functions and/or the gradient information are only accessible through noisy evaluations. Stochastic gradient (SG) descent---a first-order algorithm and a workhorse of much machine learning---is perhaps the most famous form of SA. Among all SA algorithms, the second-order simultaneous perturbation stochastic approximation (2SPSA) and the second-order stochastic gradient (2SG) are particularly efficient in handling high-dimensional problems, covering both gradient-free and gradient-based scenarios. However, due to the necessary matrix operations, the per-iteration floating-point-operations (FLOPs) cost of the standard 2SPSA/2SG is $O(p^3)$, where $p$ is the dimension of the underlying parameter. Note that the $O(p^3)$ FLOPs cost is distinct from the classical SPSA-based per-iteration $O(1)$ cost in terms of the number of noisy function evaluations. In this work, we propose a technique to efficiently implement the 2SPSA/2SG algorithms via the symmetric indefinite matrix factorization and show that the FLOPs cost is reduced from $O(p^3)$ to $O(p^2)$. The formal almost sure convergence and rate of convergence for the newly proposed approach are directly inherited from the standard 2SPSA/2SG. The improvement in efficiency and numerical stability is demonstrated in two numerical studies.

math.OC↗

arXiv2016

Defect-engineered graphene for bulk supercapacitors with high energy and power densities

The development of high-energy and high-power density supercapacitors (SCs) is critical for enabling next-generation energy storage applications. Nanocarbons are excellent SC electrode materials due to their economic viability, high-surface area, and high stability. Although nanocarbons have high theoretical surface area and hence high double layer capacitance, the net amount of energy stored in nanocarbon-SCs is much below theoretical limits due to two inherent bottlenecks: i) their low quantum capacitance and ii) limited ion-accessible surface area. Here, we demonstrate that defects in graphene could be effectively used to mitigate these bottlenecks by drastically increasing the quantum capacitance and opening new channels to facilitate ion diffusion in otherwise closed interlayer spaces. Our results support the emergence of a new energy paradigm in SCs with 250% enhancement in double layer capacitance beyond the theoretical limit. Furthermore, we demonstrate prototype defect engineered bulk SC devices with energy densities 500% higher than state-of-the-art commercial SCs without compromising the power density.

cond-mat.mtrl-sci↗