#软件工程代理

3 stories · 0 in 7 days · 1 in 30 days

DeepSeek 1 LLM 1 PTA-IRT 1 Qwen 1 SWE 1 SWE-Gate 1 代码审查 1 基准测试 1

Stories, products and papers tagged "软件工程代理", newest first.

9月29日

How-to Builders18:49

Chinese content软件工程代理中的工具链效应研究

论文分析了不同工具链组件对编程助手性能的影响，帮你理解如何构建更高效的AI编程助手。

#Qwen #DeepSeek #软件工程代理 #工具链

arXiv: DeepSeek@Haichuan Hu et al. (8)Source

9月4日

PapersSelected73°11:26

SWE-Gate Benchmark for Software Agents

SWE-Gate addresses critical evaluation gaps in coding agents, which currently only test functional correctness but ignore real-world review constraints that determine patch acceptance.

#SWE-Gate #software engineering agents #LLM #functional tests

arXiv cs.AI@Xin He et al. (6)Source

9月2日

PapersSelected73°10:50

PTA-IRT Framework for SWE Agents

PTA-IRT reduces evaluation costs for AI coding assistants while maintaining accuracy, making it valuable for developers and researchers in ASEAN.

#PTA-IRT #SWE benchmarks #software engineering agents #coding assistants

arXiv cs.AI@Kefeng Duan et al. (10)Source