arXiv subjects

Huanyu Yang

Publications and source records attributed to Huanyu Yang.

9 recordsLinked to original sources

arXiv2026

SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories

Modern coding agents increasingly appear capable of following complex software requirements, yet their success leaves a critical ambiguity: do they resolve the active specification, or merely follow the most salient path by which it was stated? We identify specification-path sensitivity, a failure mode in which requirement histories that are equivalent in their final meaning lead the same agent system to produce behaviorally different programs. This reframes evolving-requirement evaluation as active-contract resolution: before writing code, an agent must determine which requirements still count. Building on this view, we introduce SpecPath, a diagnostic evaluation that holds the repository, final contract, verifier, agent system, and execution budget fixed while changing only the revision path that leads to the contract. Rather than treating each patch as an isolated pass or failure, SpecPath uses paired executable outcomes to reveal whether an agent realizes the same tested behavior across contract-equivalent histories. Across five calibrated software tasks and fourteen coding-agent configurations, aggregate direct and revision-history accuracy is nearly unchanged; nevertheless, 35 of 100 complete blocks that succeed on the direct specification fail on at least one equivalent history. These results show that implementation success on a consolidated request does not guarantee specification-path invariance. Evaluating evolving requirements therefore calls for controlled tests of whether agents are robust to the path by which a specification becomes final.

cs.SE↗

arXiv2026

CLMASP: Coupling Large Language Models with Answer Set Programming for Robotic Task Planning

Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be executable for the specified robot with certain restrictions. This paper introduces CLMASP, an approach that couples LLMs with Answer Set Programming (ASP) to overcome the limitations, where ASP is a non-monotonic logic programming formalism renowned for its capacity to represent and reason about a robot's action knowledge. CLMASP initiates with a LLM generating a basic skeleton plan, which is subsequently tailored to the specific scenario using a vector database. This plan is then refined by an ASP program with a robot's action knowledge, which integrates implementation details into the skeleton, grounding the LLM's abstract outputs in practical robot contexts. Our experiments conducted on the VirtualHome platform demonstrate CLMASP's efficacy. Compared to the baseline executable rate of under 2% with LLM approaches, CLMASP significantly improves this to over 90%.

cs.AI↗

arXiv2026

A Four-Valued Normative Intermediate Representation for ASP-Oriented Compliance Reasoning

Technical-standard compliance reasoning may involve incomplete evidence, inconsistent observations, exceptions, and derived normative outputs. This paper presents \textsc{Monir}, a four-valued normative intermediate representation for ASP-oriented compliance workflows. \textsc{Monir} separates factual support from normative outputs: facts are represented by positive and negative support bits, while deontic labels are rule-generated output constructors interpreted by aggregation policies. Its core semantics is a staged transition system over support configurations. We define the language, rule-state interface, diagnostics, and policy-parametric reporting; characterize admissible staged evaluation by a dependency graph; prove deterministic polynomial-time evaluation for fixed evidence; and give NP/coNP upper bounds, with matching hardness for representative completion-based verdict queries.

cs.AI↗

arXiv2024

LDP: A Local Diffusion Planner for Efficient Robot Navigation and Collision Avoidance

The conditional diffusion model has been demonstrated as an efficient tool for learning robot policies, owing to its advancement to accurately model the conditional distribution of policies. The intricate nature of real-world scenarios, characterized by dynamic obstacles and maze-like structures, underscores the complexity of robot local navigation decision-making as a conditional distribution problem. Nevertheless, leveraging the diffusion model for robot local navigation is not trivial and encounters several under-explored challenges: (1) Data Urgency. The complex conditional distribution in local navigation needs training data to include diverse policy in diverse real-world scenarios; (2) Myopic Observation. Due to the diversity of the perception scenarios, diffusion decisions based on the local perspective of robots may prove suboptimal for completing the entire task, as they often lack foresight. In certain scenarios requiring detours, the robot may become trapped. To address these issues, our approach begins with an exploration of a diverse data generation mechanism that encompasses multiple agents exhibiting distinct preferences through target selection informed by integrated global-local insights. Then, based on this diverse training data, a diffusion agent is obtained, capable of excellent collision avoidance in diverse scenarios. Subsequently, we augment our Local Diffusion Planner, also known as LDP by incorporating global observations in a lightweight manner. This enhancement broadens the observational scope of LDP, effectively mitigating the risk of becoming ensnared in local optima and promoting more robust navigational decisions.

cs.RO↗

arXiv2024

Strong convergence rates for full-discrete approximations of the stochastic Allen-Cahn equations on 2D torus

In this paper we construct space-time full discretizations of stochastic Allen-Cahn equations driven by space-time white noise on 2D torus. The approximations are implemented by tamed exponential Euler discretization in time and spectral Galerkin method in space. We finally obtain the convergence rates with the spatial order of $α-δ$ and the temporal order of $α/{6}-δ$ in $\mathcal C^{-α}$ for $α\in(0,1/3)$ and $δ>0$ arbitrarily small.

math.PR↗

arXiv2024

Weak coupling limit of a Brownian particle in the curl of the 2D GFF

In this article, we study the weak coupling limit of the following equation in $\mathbb{R}^2$: $$dX_t^\varepsilon=\frac{\hatλ}{\sqrt{\log\frac1\varepsilon}}ω^\varepsilon(X_t^\varepsilon)dt+νdB_t,\quad X_0^\varepsilon=0. $$ Here $ω^\varepsilon=\nabla^{\perp}ρ_\varepsilon*ξ$ with $ξ$ representing the $2d$ Gaussian Free Field (GFF) and $ρ_\varepsilon$ denoting an appropriate identity. $B_t$ denotes a two-dimensional standard Brownian motion, and $\hatλ,ν>0$ are two given constants. We use the approach from \cite{Cannizzaro.2023} to show that the second moment of $X_t^\varepsilon$ under the annealed law converges to $(c(ν)^2+2ν^2)t$ with a precisely determined constant $c(ν)>0$, which implies a non-trivial limit of the drift terms as $\varepsilon$ vanishes. We also prove that in this weak coupling regime, the sequence of solutions converges in distribution to $\left(\sqrt{\frac{c(ν)^2}{2}+ν^2}\right)\widetilde{B}_t$ as $\varepsilon$ vanishes, where $\widetilde{B}_t$ is a two-dimensional standard Brownian motion.

math.PR↗

arXiv2024

Self-Adjusting Prescribed Performance Control for Nonlinear Systems with Input Saturation

Among the existing works on enhancing system performance via prescribed performance functions (PPFs), the decay rates of PPFs need to be predetermined by the designer, directly affecting the convergence time of the closed-loop system. However, if only considering accelerating the system convergence by selecting a big decay rate of the performance function, it may lead to the severe consequence of closed-loop system failure when considering the prevalent actuator saturation in practical scenarios. To address this issue, this work proposes a control scheme that can flexibly self-adjust the convergence rates of the performance functions (PFs), aiming to achieve faster steady-state convergence while avoiding the risk of error violation beyond the PFs' envelopes, which may arise from input saturation and improper decay rate selection in traditional prescribed performance control (PPC) methods. Specifically, a performance index function (PIF) is introduced as a reference criterion, based on which the self-adjusting rates of the PFs are designed for different cases, exhibiting the following appealing features: 1) It can eliminate the need to prespecify the initial values of the PFs. In addition, it can also accommodate arbitrary magnitudes of initial errors while avoiding excessive initial control efforts. 2) Considering actuator saturation, this method can not only reduce the decay rates of the PFs when necessary to avoid violation of the PFs, but also increase the decay rates to accelerate system convergence when there is remaining control capacity. Finally, several numerical simulations are conducted to confirm the effectiveness and superiority of the proposed method.

eess.SY↗

arXiv2020

Conservative stochastic 2-dimensional Cahn-Hilliard equation

We consider the stochastic 2-dimensional Cahn-Hilliard equation which is driven by the derivative in space of a space-time white noise. We use two different approaches to study this equation. First we prove that there exists a unique solution $Y$ to the shifted equation (see (1.4) below), then $X:=Y+{Z}$ is the unique solution to stochastic Cahn-Hilliard equaiton, where ${Z}$ is the corresponding O-U process. Moreover, we use Dirichlet form approach in \cite{Albeverio:1991hk} to construct the probabilistically weak solution the the original equation (1.1) below. By clarifying the precise relation between the solutions obtained by the Dirichlet forms aprroach and $X$, we can also get the restricted Markov uniquness of the generator and the uniqueness of martingale solutions to the equation (1.1).

math.PR↗

arXiv2019

Weak solutions to the sharp interface limit of stochastic Cahn-Hilliard equations

We study the asymptotic limit, as $\varepsilon\searrow 0$, of solutions of the stochastic Cahn-Hilliard equation: $$ \partial_t u^\varepsilon=Δ\left(-\varepsilonΔu^\varepsilon+\frac{1}{\varepsilon}f(u^\varepsilon)\right)+\dot{\mathcal{W}}^\varepsilon_t, \\ $$ where $\mathcal{W}^\varepsilon=\varepsilon^σW$ or $\mathcal{W}^\varepsilon=\varepsilon^σW^\varepsilon$, $W$ is a $Q$-Wiener process and $W^\varepsilon$ is smooth in time and converges to $W$ as $\varepsilon\searrow 0$. In the case that $\mathcal{W}^\varepsilon=\varepsilon^σW$, we prove that for all $σ>\frac{1}{2}$, the solution $u^\varepsilon$ converges to a weak solution to an appropriately defined limit of the deterministic Cahn-Hilliard equation. In radial symmetric case we prove that for all $σ\geq\frac{1}{2}$, $u^\varepsilon$ converges to the deterministic Hele-Shaw model. In the case that $\mathcal{W}^\varepsilon=\varepsilon^σW^\varepsilon$, we prove that for all $σ>0$, $u^\varepsilon$ converges to the weak solution to the deterministic limit Cahn-Hilliard equation. In radial symmetric case we prove that $u^\varepsilon$ converges to deterministic Hele-Shaw model when $σ>0$ and converges to a stochastic model related to stochastic Hele-Shaw model when $σ=0$.

math.PR↗