arXiv subjects

Zihao Xia

Publications and source records attributed to Zihao Xia.

5 recordsLinked to original sources

arXiv2026

Bridging Identification and Second-Order Acceleration: A Fast Alternating Minimization Framework for Composite Optimization

We consider a class of composite optimization problems involving a smooth function and a proper, lower semicontinuous regularizer, which may be nonconvex and nonsmooth. We propose a novel alternating minimization framework that integrates proximal-gradient steps with cubic-regularized Newton updates restricted to a dynamically identified low-dimensional subspace. Under the Kurdyka--{\L}ojasiewicz (KL) property, we establish global convergence of the proposed method to a stationary point. Moreover, by incorporating an adaptive thresholding strategy guided by the KL exponent, we prove a finite identification property without imposing any nondegeneracy assumptions. We further develop a local convergence analysis and show that the proposed method attains a worst-case iteration complexity of $\mathcal{O}(\varepsilon^{-3/2})$ for achieving approximate second-order stationarity. Numerical experiments on both synthetic and real datasets demonstrate the efficiency and effectiveness of the proposed framework.

math.OC↗

arXiv2025

Aime: Towards Fully-Autonomous Multi-Agent Framework

Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) are emerging as a powerful paradigm for solving complex, multifaceted problems. However, the potential of these systems is often constrained by the prevalent plan-and-execute framework, which suffers from critical limitations: rigid plan execution, static agent capabilities, and inefficient communication. These weaknesses hinder their adaptability and robustness in dynamic environments. This paper introduces Aime, a novel multi-agent framework designed to overcome these challenges through dynamic, reactive planning and execution. Aime replaces the conventional static workflow with a fluid and adaptive architecture. Its core innovations include: (1) a Dynamic Planner that continuously refines the overall strategy based on real-time execution feedback; (2) an Actor Factory that implements Dynamic Actor instantiation, assembling specialized agents on-demand with tailored tools and knowledge; and (3) a centralized Progress Management Module that serves as a single source of truth for coherent, system-wide state awareness. We empirically evaluated Aime on a diverse suite of benchmarks spanning general reasoning (GAIA), software engineering (SWE-bench Verified), and live web navigation (WebVoyager). The results demonstrate that Aime consistently outperforms even highly specialized state-of-the-art agents in their respective domains. Its superior adaptability and task success rate establish Aime as a more resilient and effective foundation for multi-agent collaboration.

cs.AI↗

arXiv2025

A Single-loop Proximal Subgradient Algorithm for A Class Structured Fractional Programs

In this paper, we investigate a class of nonconvex and nonsmooth fractional programming problems, where the numerator composed of two parts: a convex, nonsmooth function and a differentiable, nonconvex function, and the denominator consists of a convex, nonsmooth function composed of a linear operator. These structured fractional programming problems have broad applications, including CT reconstruction, sparse signal recovery, the single-period optimal portfolio selection problem and standard Sharpe ratio minimization problem. We develop a single-loop proximal subgradient algorithm that alleviates computational complexity by decoupling the evaluation of the linear operator from the nonsmooth component. We prove the global convergence of the proposed single-loop algorithm to an exact lifted stationary point under the Kurdyka-Łojasiewicz assumption. Additionally, we present a practical variant incorporating a nonmonotone line search to improve computational efficiency. Finally, through extensive numerical simulations, we showcase the superiority of the proposed approach over the existing state-of-the-art methods for three applications: $L_{1}/S_κ$ sparse signal recovery, limited-angle CT reconstruction, and optimal portfolio selection.

math.OC↗

arXiv2024

Robust Policy Learning for Multi-UAV Collision Avoidance with Causal Feature Selection

In unseen and complex outdoor environments, collision avoidance navigation for unmanned aerial vehicle (UAV) swarms presents a challenging problem. It requires UAVs to navigate through various obstacles and complex backgrounds. Existing collision avoidance navigation methods based on deep reinforcement learning show promising performance but suffer from poor generalization abilities, resulting in performance degradation in unseen environments. To address this issue, we investigate the cause of weak generalization ability in DRL and propose a novel causal feature selection module. This module can be integrated into the policy network and effectively filters out non-causal factors in representations, thereby reducing the influence of spurious correlations between non-causal factors and action predictions. Experimental results demonstrate that our proposed method can achieve robust navigation performance and effective collision avoidance especially in scenarios with unseen backgrounds and obstacles, which significantly outperforms existing state-of-the-art algorithms.

cs.RO↗

arXiv2024

Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation Disentanglement

Deep reinforcement learning (DRL) has achieved remarkable progress in online path planning tasks for multi-UAV systems. However, existing DRL-based methods often suffer from performance degradation when tackling unseen scenarios, since the non-causal factors in visual representations adversely affect policy learning. To address this issue, we propose a novel representation learning approach, \ie, causal representation disentanglement, which can identify the causal and non-causal factors in representations. After that, we only pass causal factors for subsequent policy learning and thus explicitly eliminate the influence of non-causal factors, which effectively improves the generalization ability of DRL models. Experimental results show that our proposed method can achieve robust navigation performance and effective collision avoidance especially in unseen scenarios, which significantly outperforms existing SOTA algorithms.

cs.RO↗