arXiv subjects

Xin Pang

Publications and source records attributed to Xin Pang.

4 recordsLinked to original sources

arXiv2026

Materials Acceleration Platform for Electrochemistry: a Platform for Autonomous Electrochemistry

Corrosion testing is slow, labor-intensive, and sensitive to operator technique, limiting the generation of large, high-quality datasets for data-driven materials discovery. The Materials Acceleration Platform for Electrochemistry (MAP-E) is an autonomous, high-throughput system, capable of performing parallel electrochemical experiments. It integrates robotic liquid handling, sample transfer with a multi-channel potentiostatic control to extract corrosion metrics without human intervention. Validation against an ASTM G61-analog benchmark demonstrates good reproducibility, with a standard deviation of 75 mV in pitting potential across 32 automated measurements. The platform was then employed to autonomously construct pH-chloride stability diagrams for 304 stainless steel using an uncertainty-driven sampling strategy on a Gaussian process surrogate model. This approach reduces operator involvement and accelerates the exploration of environmental spaces. The MAP-E establishes a framework for autonomous electrochemical experimentation, enabling generation of corrosion datasets that inform materials discovery, alloy design, and durability assessment in service environments.

cond-mat.mtrl-sci↗

arXiv2025

SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection

Retrieval-Augmented Generation (RAG) enhances language models by incorporating external knowledge at inference time. However, graph-based RAG systems often suffer from structural overhead and imprecise retrieval: they require costly pipelines for entity linking and relation extraction, yet frequently return subgraphs filled with loosely related or tangential content. This stems from a fundamental flaw -- semantic similarity does not imply semantic relevance. We introduce SlimRAG, a lightweight framework for retrieval without graphs. SlimRAG replaces structure-heavy components with a simple yet effective entity-aware mechanism. At indexing time, it constructs a compact entity-to-chunk table based on semantic embeddings. At query time, it identifies salient entities, retrieves and scores associated chunks, and assembles a concise, contextually relevant input -- without graph traversal or edge construction. To quantify retrieval efficiency, we propose Relative Index Token Utilization (RITU), a metric measuring the compactness of retrieved content. Experiments across multiple QA benchmarks show that SlimRAG outperforms strong flat and graph-based baselines in accuracy while reducing index size and RITU (e.g., 16.31 vs. 56+), highlighting the value of structure-free, entity-centric context selection. The code will be released soon. https://github.com/continue-ai-company/SlimRAG

cs.IR↗

arXiv2025

AI2Agent: An End-to-End Framework for Deploying AI Projects as Autonomous Agents

As AI technology advances, it is driving innovation across industries, increasing the demand for scalable AI project deployment. However, deployment remains a critical challenge due to complex environment configurations, dependency conflicts, cross-platform adaptation, and debugging difficulties, which hinder automation and adoption. This paper introduces AI2Agent, an end-to-end framework that automates AI project deployment through guideline-driven execution, self-adaptive debugging, and case \& solution accumulation. AI2Agent dynamically analyzes deployment challenges, learns from past cases, and iteratively refines its approach, significantly reducing human intervention. To evaluate its effectiveness, we conducted experiments on 30 AI deployment cases, covering TTS, text-to-image generation, image editing, and other AI applications. Results show that AI2Agent significantly reduces deployment time and improves success rates. The code and demo video are now publicly accessible.

cs.AI↗

arXiv2024

AI2Apps: A Visual IDE for Building LLM-based AI Agent Applications

We introduce AI2Apps, a Visual Integrated Development Environment (Visual IDE) with full-cycle capabilities that accelerates developers to build deployable LLM-based AI agent Applications. This Visual IDE prioritizes both the Integrity of its development tools and the Visuality of its components, ensuring a smooth and efficient building experience.On one hand, AI2Apps integrates a comprehensive development toolkit ranging from a prototyping canvas and AI-assisted code editor to agent debugger, management system, and deployment tools all within a web-based graphical user interface. On the other hand, AI2Apps visualizes reusable front-end and back-end code as intuitive drag-and-drop components. Furthermore, a plugin system named AI2Apps Extension (AAE) is designed for Extensibility, showcasing how a new plugin with 20 components enables web agent to mimic human-like browsing behavior. Our case study demonstrates substantial efficiency improvements, with AI2Apps reducing token consumption and API calls when debugging a specific sophisticated multimodal agent by approximately 90% and 80%, respectively. The AI2Apps, including an online demo, open-source code, and a screencast video, is now publicly accessible.

cs.AI↗