8 citations · 14 across the 7 of their papers we have counts for
7 papers
OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development
Li Li, Han Hu, Tianjian Zhang +27
We present OPENHARMONY BENCH, an app-level coding benchmark for evaluating LLM-based coding agents on OpenHarmony ArkTS applications. Unlike function-level benchmarks, it evaluates…
FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows
Shuo Hao, You Lu, Bihuan Chen +1
Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into…
DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
You Lu, Kun Zhang, Bihuan Chen +1
Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM agents. Exi…
Lifting the Veil on Composition, Risks, and Mitigations of the Large Language Model Supply Chain
Kaifeng Huang, Bihuan Chen, You Lu +7
Large language models (LLMs) have sparked significant impact with regard to both intelligence and productivity. Numerous enterprises have integrated LLMs into their applications to…
Detecting and Fixing Violations of Modification Terms in Open Source Licenses during Forking
Kaifeng Huang, Yingfeng Xia, Bihuan Chen +3
Open source software brings benefit to software community, but also introduces legal risks caused by license violations, which result in serious consequences such as lawsuits and f…
Answering Uncertain, Under-Specified API Queries Assisted by Knowledge-Aware Human-AI Dialogue
Qing Huang, Zishuai Li, Zhenchang Xing +4
Developers' API needs should be more pragmatic, such as seeking suggestive, explainable, and extensible APIs rather than the so-called best result. Existing API search research can…
RARE: Robust Masked Graph Autoencoder
Wenxuan Tu, Qing Liao, Sihang Zhou +5
Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perf…