Searcharxiv⌕ Search

arXiv subjects

Han Luo

Publications and source records attributed to Han Luo.

15 recordsLinked to original sources
arXiv2026

Quantum Algorithm for Elliptic Curve Discrete Logarithms with Space-Efficient Point Addition

The Elliptic Curve Discrete Logarithm Problem (ECDLP) is a fundamental problem in cryptography, and reducing the resource requirements of quantum algorithms for solving ECDLP is an important goal. In this work, we present a space-efficient quantum algorithm for solving the ECDLP over prime fields, achieving an implementation with only $3n+6\lfloor \log_2 n \rfloor+O(1)$ logical qubits and $1056n^3/\log_2 n+O(n^2)$ Toffoli gates, where $n$ is the bit-length of the prime. For a 256-bit prime-field curve, our construction requires only 835 logical qubits, reducing the previous best estimates of 1098 and 1175 logical qubits by Chevignard et al. [EUROCRYPT 2026] and Babbush et al. [ArXiv Preprint 2026], respectively. The key to our improvement is a new space-efficient reversible modular inversion circuit, which addresses the dominant space bottleneck in affine-coordinate point addition. Starting from the extended Euclidean algorithm (EEA), we refine the register-sharing technique of Proos and Zalka by introducing length registers and location-controlled arithmetic to compactly store and update intermediate variables. We further optimize the reversible update procedures and construct the corresponding controlled arithmetic circuits, resulting in a modular inversion circuit implemented by only $2n+6\lfloor \log_2 n \rfloor+O(1)$ logical qubits and $229n^2+O(n\log_2 n)$ Toffoli gates. This modular inversion circuit together with mid-circuit measurements and classical feed-forward operations provides a space-efficient controlled affine point-addition circuit and a complete implementation of Shor's algorithm for ECDLP.

quant-ph↗
arXiv2026

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is well specified or achievable in the available environment. In such cases, a reliable agent should recognize that further interaction is unlikely to help and abstain from additional tool calls. We define Agentic Abstention, the problem of deciding when an agent should stop acting under uncertainty. Unlike standard LLM abstention, which is usually evaluated as a single-turn answer-or-abstain decision, agentic abstention is a sequential decision problem: an agent can answer, abstain, or gather more information at each turn, and the need to abstain may only become clear after interacting with the environment. We study this problem across web shopping, terminal environments, and question answering, evaluating 13 LLM-as-agent systems and 2 agent scaffolds on more than 28,000 tasks. Our results show that the main challenge is not only whether agents can abstain, but also when they abstain. Some agents never abstain when they should, while others do so only after many unnecessary interactions. This gap is especially large on tasks where the instruction appears feasible until the environment reveals otherwise (e.g., no valid result matches the instruction). We further find that model scale, reasoning, and agent scaffolding affect abstention in different ways, where larger or more capable models sometimes perform worse at timely abstention. Finally, we introduce CONVOLVE, a context engineering method for improving agentic abstention that distills full interaction trajectories into reusable stopping rules. On WebShop, CONVOLVE substantially improves timely abstention without updating model parameters, raising Llama-3.3-70B's timely recall rate from 26.7 to 57.4. Our dataset and code are available at https://lhannnn.github.io/agentic-abstention

cs.AI↗
arXiv2026

Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation

Vision-Language Models (VLMs) have demonstrated exceptional general reasoning capabilities. However, their performance in embodied navigation remains hindered by a scarcity of aligned open-world vision and robot control data. Despite simulators providing a cost-effective alternative for data collection, the inherent reliance on photorealistic simulations often limits the transferability of learned policies. To this end, we propose \textit{\textbf{S}andbox-\textbf{A}bstracted \textbf{G}rounded \textbf{E}xperience} (\textbf{\textit{SAGE}}), a framework that enables agents to learn within a physics-grounded semantic abstraction rather than a photorealistic simulation, mimicking the human capacity for mental simulation where plans are rehearsed in simplified physics abstractions before execution. \textit{SAGE} system operates via three synergistic phases: (1) \textit{Genesis}: constructing diverse, physics-constrained semantic environments to bootstrap experience; (2) \textit{Evolution}: distilling experiences through Reinforcement Learning (RL), utilizing a novel asymmetric adaptive clipping mechanism to stabilize updates; (3) \textit{Navigation}: bridging the abstract policy to open-world control. We demonstrate that \textit{SAGE} significantly improves planner-assisted embodied navigation, achieving a 53.21\% LLM-Match Success Rate on A-EQA (+9.7\% over baseline), while showing encouraging transfer to physical indoor robot deployment.

cs.RO↗
arXiv2026

SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation

Large language models are increasingly deployed in multi-turn settings such as tutoring, support, and counseling, where reliability depends on preserving consistent roles, personas, and goals across long horizons. This requirement becomes critical when LLMs are used to generate synthetic dialogues for training and evaluation, since LLM--LLM conversations can accumulate identity-related failures such as persona drift, role confusion, and "echoing", where one agent gradually mirrors its partner. We introduce SPASM (Stable Persona-driven Agent Simulation for Multi-turn dialogue generation), a modular, stability-first framework that decomposes simulation into (i) persona creation via schema sampling, plausibility validation, and natural-language persona crafting, (ii) Client--Responder dialogue generation, and (iii) termination detection for coherent stopping. To improve long-horizon stability without changing model weights, we propose Egocentric Context Projection (ECP): dialogue history is stored in a perspective-agnostic representation and deterministically projected into each agent's egocentric view before generation. Across three LLM backbones (GPT-4o-mini, DeepSeek-V3.2, Qwen-Plus) and nine Client--Responder pairings, we construct a dataset of 4,500 personas and 45,000 conversations (500 personas X 10 conversations per pairing). Ablations show ECP substantially reduces persona drift and, under human validation, eliminates echoing; embedding analyses recover persona structure and reveal strong responder-driven interaction geometry. Our code is available at https://github.com/lhannnn/SPASM.

cs.CL↗
arXiv2026

Space-Efficient Quantum Algorithm for Elliptic Curve Discrete Logarithms with Resource Estimation

Solving the Elliptic Curve Discrete Logarithm Problem (ECDLP) is critical for evaluating the quantum security of widely deployed elliptic-curve cryptosystems. Consequently, minimizing the number of logical qubits required to execute this algorithm is a key object. In implementations of Shor's algorithm, the space complexity is largely dictated by the modular inversion operation during point addition. Starting from the extended Euclidean algorithm (EEA), we refine the register-sharing method of Proos and Zalka and propose a space-efficient reversible modular inversion algorithm. We use length registers together with location-controlled arithmetic to store the intermediate variables in a compact form throughout the computation. We then optimize the stepwise update rules and give concrete circuit constructions for the resulting controlled arithmetic components. This leads to a modular inversion circuit that uses $3n + 4\lfloor \log_2 n \rfloor + O(1)$ logical qubits and $204n^2\log_2 n + O(n^2)$ Toffoli gates. By inserting this modular inversion component into the controlled affine point-addition circuit, we obtain a space-efficient algorithm for the ECDLP with $5n + 4\lfloor \log_2 n \rfloor + O(1)$ qubits and $O(n^3)$ Toffoli gates. In particular, for a 256-bit prime-field curve, our estimate reduces the logical-qubit count to 1333, compared with 2124 in the previous low-width implementation of H\"aner et al.

quant-ph↗
arXiv2026

PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning

Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However, long-horizon multi-step tool planning is challenging, because the exploration space suffers from a combinatorial explosion. In this scenario, even when a correct tool-use path is found, it is usually considered an immediate reward for current training, which would not provide any reusable information for subsequent training. In this paper, we argue that historically successful trajectories contain reusable tool-transition patterns, which can be leveraged throughout the whole training process. Inspired by ant colony optimization where historically successful paths can be reflected by the pheromone, we propose Pheromone-Guided Policy Optimization (PhGPO), which learns a trajectory-based transition pattern (i.e., pheromone) from historical trajectories and then uses the learned pheromone to guide policy optimization. This learned pheromone provides explicit and reusable guidance that steers policy optimization toward historically successful tool transitions, thereby improving long-horizon tool planning. Comprehensive experimental results demonstrate the effectiveness of our proposed PhGPO.

cs.AI↗
arXiv2025

DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses

Large language models (LLMs) now mediate many web-based mental-health, crisis, and other emotionally sensitive services, yet their psychosocial safety in these settings remains poorly understood and weakly evaluated. We present DialogGuard, a multi-agent framework for assessing psychosocial risks in LLM-generated responses along five high-severity dimensions: privacy violations, discriminatory behaviour, mental manipulation, psychological harm, and insulting behaviour. DialogGuard can be applied to diverse generative models through four LLM-as-a-judge pipelines, including single-agent scoring, dual-agent correction, multi-agent debate, and stochastic majority voting, grounded in a shared three-level rubric usable by both human annotators and LLM judges. Using PKU-SafeRLHF with human safety annotations, we show that multi-agent mechanisms detect psychosocial risks more accurately than non-LLM baselines and single-agent judging; dual-agent correction and majority voting provide the best trade-off between accuracy, alignment with human ratings, and robustness, while debate attains higher recall but over-flags borderline cases. We release Dialog-Guard as open-source software with a web interface that provides per-dimension risk scores and explainable natural-language rationales. A formative study with 12 practitioners illustrates how it supports prompt design, auditing, and supervision of web-facing applications for vulnerable users.

cs.AI↗
arXiv2025

Increase of critical current density in FeSe superconductor by strain effect

Conventional $J_c$-enhancement methods like doping and irradiation often introduce extrinsic elements or defects, altering intrinsic properties. Here, we report a significant $J_c$ enhancement in FeSe single crystals through compressive strain applied using a glass-fiber-reinforced plastic substrate with anisotropic thermal contraction during cooling. Under zero field at 2 K, $J_{\text{c}}$ increases by a factor of $\sim$4 from $\sim 2.3 \times 10^{4}$ to $\sim 8.7 \times 10^{4}$ A cm$^{-2}$; at 5 T, it achieves an order-of-magnitude enhancement, rising from $\sim 1.0 \times 10^{3}$ to $\sim 1.0 \times 10^{4}$ A cm$^{-2}$. Analysis based on the Dew-Hughes model of the $f_{\text{p}}$(h) relationship shows that strain strengthens vortex pinning, and shifts the pinning mechanism from point-like pinning to combined point and surface pinnings. This work offers an effective method to enhance FeSe's current-carrying limitation, deepens understanding of iron-based superconductors' pinning mechanisms, and highlights strain engineering's potential for optimizing superconducting performance.

cond-mat.supr-con↗
arXiv2025

AICrypto: Evaluating Cryptography Capabilities of Large Language Models

We build \textbf{AICrypto}, a comprehensive benchmark designed to evaluate the cryptography capabilities of large language models (LLMs). The benchmark comprises 135 multiple-choice questions, 150 capture-the-flag challenges, and 30 proof problems, covering a broad range of skills from knowledge memorization to vulnerability exploitation and formal reasoning. All tasks are carefully reviewed or constructed by cryptography experts to improve correctness and rigor. For each proof problem, we provide detailed scoring rubrics and reference solutions that enable automated grading, achieving high correlation with human expert evaluations. We introduce strong human expert performance baselines for comparison across all task types. Our evaluation of 17 leading LLMs reveals that state-of-the-art models match or even surpass human experts in memorizing cryptographic concepts, exploiting common vulnerabilities, and routine proofs. However, our analysis reveals that they still lack a deep understanding of abstract mathematical concepts and struggle with tasks that require multi-step reasoning and dynamic analysis. We hope this work could provide insights for future research on LLMs in cryptographic applications. Our code and dataset are available at https://github.com/wangyu-ovo/aicrypto-agent.

cs.CR↗
arXiv2024

Liouville theorem for $V$-harmonic heat flows

In this paper, we investigate $V$-harmonic heat flows from complete Riemannian manifolds with nonnegative Bakry-Emery Ricci curvature to complete Riemannian manifolds with sectional curvature bounded above. We give a gradient estimate of ancient solutions to this flow and establish a Liouville type theorem.

math.DG↗
arXiv2024

Hierarchical Attention and Parallel Filter Fusion Network for Multi-Source Data Classification

Hyperspectral image (HSI) and synthetic aperture radar (SAR) data joint classification is a crucial and yet challenging task in the field of remote sensing image interpretation. However, feature modeling in existing methods is deficient to exploit the abundant global, spectral, and local features simultaneously, leading to sub-optimal classification performance. To solve the problem, we propose a hierarchical attention and parallel filter fusion network for multi-source data classification. Concretely, we design a hierarchical attention module for hyperspectral feature extraction. This module integrates global, spectral, and local features simultaneously to provide more comprehensive feature representation. In addition, we develop parallel filter fusion module which enhances cross-modal feature interactions among different spatial locations in the frequency domain. Extensive experiments on two multi-source remote sensing data classification datasets verify the superiority of our proposed method over current state-of-the-art classification approaches. Specifically, our proposed method achieves 91.44% and 80.51% of overall accuracy (OA) on the respective datasets, highlighting its superior performance.

eess.IV↗
arXiv2023

LWE with Quantum Amplitudes: Algorithm, Hardness, and Oblivious Sampling

In this paper, we show new algorithms, hardness results and applications for $\sf{S|LWE\rangle}$ and $\sf{C|LWE\rangle}$ with real Gaussian, Gaussian with linear or quadratic phase terms, and other related amplitudes. Let $n$ be the dimension of LWE samples. Our main results are 1. There is a $2^{\tilde{O}(\sqrt{n})}$-time algorithm for $\sf{S|LWE\rangle}$ with Gaussian amplitude with \emph{known} phase, given $2^{\tilde{O}(\sqrt{n})}$ many quantum samples. The algorithm is modified from Kuperberg's sieve, and in fact works for more general amplitudes as long as the amplitudes and phases are completely \emph{known}. 2. There is a polynomial time quantum algorithm for solving $\sf{S|LWE\rangle}$ and $\sf{C|LWE\rangle}$ for Gaussian with quadratic phase amplitudes, where the sample complexity is as small as $\tilde{O}(n)$. As an application, we give a quantum oblivious LWE sampler where the core quantum sampler requires only quasi-linear sample complexity. This improves upon the previous oblivious LWE sampler given by Debris-Alazard, Fallahpour, Stehl\'{e} [STOC 2024], whose core quantum sampler requires $\tilde{O}(nr)$ sample complexity, where $r$ is the standard deviation of the error. 3. There exist polynomial time quantum reductions from standard LWE or worst-case GapSVP to $\sf{S|LWE\rangle}$ with Gaussian amplitude with small \emph{unknown} phase, and arbitrarily many samples. Compared to the first two items, the appearance of the unknown phase term places a barrier in designing efficient quantum algorithm for solving standard LWE via $\sf{S|LWE\rangle}$.

quant-ph↗
arXiv2022

Gradient Estimate of subelliptic harmonic maps with potential

In this paper, we investigate subelliptic harmonic maps with potential from noncompact complete sub-Riemannian manifolds corresponding to totally geodesic Riemannian foliations. Under some suitable conditions, we give the gradient estimates of these maps and establish a Liouville type result.

math.DG↗
arXiv2022

On subelliptic harmonic maps with potential

Let $(M,H,g_H;g)$ be a sub-Riemannian manifold and $(N,h)$ be a Riemannian manifold. For a smooth map $u: M \to N$, we consider the energy functional $E_G(u) = \frac{1}{2} \int_M[|\mathrm{d}u_H|^2-2G(u)] \mathrm{d}V_M$, where $\mathrm{d}u_H$ is the horizontal differential of $u$, $G:N\to \mathbb{R}$ is a smooth function on $N$. The critical maps of $E_G(u)$ are referred to as subelliptic harmonic maps with potential $G$. In this paper, we investigate the existence problem for subelliptic harmonic maps with potentials by a subelliptic heat flow. Assuming that the target Riemannian manifold has non-positive sectional curvature and the potential $G$ satisfies various suitable conditions, we prove some Eells-Sampson type existence results when the source manifold is either a step-$2$ sub-Riemannian manifold or a step-$r$ sub-Riemannian manifold whose sub-Riemannian structure comes from a tense Riemannian foliation.

math.DG↗