feat: 中文版添加自动翻译功能
- 使用 Google Translate API 翻译标题和摘要 - 添加翻译缓存避免重复翻译 - 中文版内容全部为中文（除链接外）
This commit is contained in:
parent
7a46cc2e04
commit
28c290966f
2
cache/seen_urls.json
vendored
2
cache/seen_urls.json
vendored
@ -1,5 +1,5 @@
|
||||
{
|
||||
"lastUpdate": "2026-02-27T15:40:01.951Z",
|
||||
"lastUpdate": "2026-02-27T15:43:08.320Z",
|
||||
"urls": [
|
||||
"http://arxiv.org/abs/2602.23360v1",
|
||||
"http://arxiv.org/abs/2602.23359v1",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# AI Daily Brief - 2026-02-27
|
||||
|
||||
> Collected at: 2/27/2026, 11:40:01 PM
|
||||
> Collected at: 2/27/2026, 11:43:08 PM
|
||||
> Total items: 131
|
||||
|
||||
## 🔥 Top 10 Highlights
|
||||
|
||||
@ -1,57 +1,57 @@
|
||||
# AI Daily Brief - 2026-02-27
|
||||
|
||||
> 采集时间: 2026/2/27 23:40:01
|
||||
> 采集时间: 2026/2/27 23:42:19
|
||||
> 总条目: 131
|
||||
|
||||
## 🔥 Top 10 重要消息
|
||||
|
||||
1. [sponsors/muratcankoylan](https://github.com/sponsors/muratcankoylan) - **GitHub Trending**
|
||||
> A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimi...
|
||||
1. [赞助商/muratcankoylan](https://github.com/sponsors/muratcankoylan) - **GitHub Trending**
|
||||
> 用于上下文工程、多代理架构和生产代理系统的代理技能的全面集合。在构建、优化或调试需要有效的代理系统时使用
|
||||
|
||||
2. [login?return_to=%2Fruvnet%2Fclaude-flow](https://github.com/login?return_to=%2Fruvnet%2Fclaude-flow) - **GitHub Trending**
|
||||
> 🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversation...
|
||||
2. [登录？return_to=%2Fruvnet%2Fclaude-flow](https://github.com/login?return_to=%2Fruvnet%2Fclaude-flow) - **GitHub Trending**
|
||||
> 🌊 Claude 领先的代理编排平台。部署智能多代理群、协调自主工作流程并构建对话式 AI 系统。具有企业级架构师功能
|
||||
|
||||
3. [Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization](https://huggingface.co/papers/2602.22675) - **Hugging Face**
|
||||
> Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-inte...
|
||||
3. [多搜索，少思考：重新思考长期代理搜索的效率和泛化](https://huggingface.co/papers/2602.22675) - **Hugging Face**
|
||||
> 最近的深度研究代理主要通过扩展推理深度来提高性能，但这会导致搜索密集型场景中的推理成本和延迟较高。此外，跨 h 的泛化
|
||||
|
||||
4. [AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning](https://huggingface.co/papers/2602.23258) - **Hugging Face**
|
||||
> While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual par...
|
||||
4. [AgentDropoutV2：通过测试时纠正或拒绝修剪优化多代理系统中的信息流](https://huggingface.co/papers/2602.23258) - **Hugging Face**
|
||||
> 虽然多智能体系统（MAS）在复杂推理方面表现出色，但它们却受到个体参与者生成的错误信息的连锁影响。当前的解决方案通常采用刚性的
|
||||
|
||||
5. [Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling](https://huggingface.co/papers/2602.21760) - **Hugging Face**
|
||||
> Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensiv...
|
||||
5. [基于条件指导调度的混合数据管道并行加速扩散](https://huggingface.co/papers/2602.21760) - **Hugging Face**
|
||||
> 扩散模型在高保真图像、视频和音频生成方面取得了显着进展，但推理的计算成本仍然很高。尽管如此，电流扩散加速了我
|
||||
|
||||
6. [Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization](https://huggingface.co/papers/2602.23008) - **Hugging Face**
|
||||
> Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained kno...
|
||||
6. [通过混合策略优化的探索性内存增强 LLM 代理](https://huggingface.co/papers/2602.23008) - **Hugging Face**
|
||||
> 探索仍然是通过强化学习训练的大型语言模型智能体的关键瓶颈。虽然先前的方法利用了预先训练的知识，但它们在需要深度学习的环境中失败了。
|
||||
|
||||
7. [login?return_to=%2Fruvnet%2Fwifi-densepose](https://github.com/login?return_to=%2Fruvnet%2Fwifi-densepose) - **GitHub Trending**
|
||||
> Production-ready implementation of InvisPose - a revolutionary WiFi-based dense human pose estimation system that enables real-time full-body tracking...
|
||||
7. [登录？return_to=%2Fruvnet%2Fwifi-densepose](https://github.com/login?return_to=%2Fruvnet%2Fwifi-densepose) - **GitHub Trending**
|
||||
> InvisPose 的生产就绪实施 - 一种基于 WiFi 的革命性密集人体姿势估计系统，可使用商用网状路由器实现穿墙实时全身跟踪
|
||||
|
||||
8. [login?return_to=%2Fbytedance%2Fdeer-flow](https://github.com/login?return_to=%2Fbytedance%2Fdeer-flow) - **GitHub Trending**
|
||||
> An open-source SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skills and subagents, it handles d...
|
||||
8. [登录?return_to=%2Fbytedance%2Fdeer-flow](https://github.com/login?return_to=%2Fbytedance%2Fdeer-flow) - **GitHub Trending**
|
||||
> 一个用于研究、编码和创建的开源 SuperAgent 工具。借助沙箱、内存、工具、技能和子代理，它可以处理可能需要几分钟才能完成的不同级别的任务。
|
||||
|
||||
9. [login?return_to=%2Fmoonshine-ai%2Fmoonshine](https://github.com/login?return_to=%2Fmoonshine-ai%2Fmoonshine) - **GitHub Trending**
|
||||
> Fast and accurate automatic speech recognition (ASR) for edge devices
|
||||
9. [登录？return_to=%2Fmoonshine-ai%2Fmoonshine](https://github.com/login?return_to=%2Fmoonshine-ai%2Fmoonshine) - **GitHub Trending**
|
||||
> 适用于边缘设备的快速准确的自动语音识别 (ASR)
|
||||
|
||||
10. [sponsors/obra](https://github.com/sponsors/obra) - **GitHub Trending**
|
||||
> An agentic skills framework & software development methodology that works.
|
||||
10. [赞助商/奥布拉](https://github.com/sponsors/obra) - **GitHub Trending**
|
||||
> 有效的代理技能框架和软件开发方法。
|
||||
|
||||
## 📂 分类汇总
|
||||
|
||||
### Agent 框架
|
||||
|
||||
- [Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks](http://arxiv.org/abs/2602.23330v1) - arXiv
|
||||
- [AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning](http://arxiv.org/abs/2602.23258v1) - arXiv
|
||||
- [迈向专家投资团队：细粒度交易任务的多代理LLM系统](http://arxiv.org/abs/2602.23330v1) - arXiv
|
||||
- [AgentDropoutV2：通过测试时纠正或拒绝修剪优化多代理系统中的信息流](http://arxiv.org/abs/2602.23258v1) - arXiv
|
||||
|
||||
### AI 基础设施 / 推理优化
|
||||
|
||||
- [Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators](http://arxiv.org/abs/2602.23334v1) - arXiv
|
||||
- [Invariant Transformation and Resampling based Epistemic-Uncertainty Reduction](http://arxiv.org/abs/2602.23315v1) - arXiv
|
||||
- [Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive](http://arxiv.org/abs/2602.23239v1) - arXiv
|
||||
- [InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models](http://arxiv.org/abs/2602.23200v1) - arXiv
|
||||
- [Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent](http://arxiv.org/abs/2602.23079v1) - arXiv
|
||||
- [Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference](http://arxiv.org/abs/2602.22868v1) - arXiv
|
||||
- [Differentiable Zero-One Loss via Hypersimplex Projections](http://arxiv.org/abs/2602.23336v1) - arXiv
|
||||
- [FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification](http://arxiv.org/abs/2602.23192v1) - arXiv
|
||||
- [用于硬件加速器上运行时可重构多精度量化乘法的按位脉动阵列架构](http://arxiv.org/abs/2602.23334v1) - arXiv
|
||||
- [基于不变变换和重采样的认知不确定性减少](http://arxiv.org/abs/2602.23315v1) - arXiv
|
||||
- [代理和架构限制：为什么基于优化的系统无法响应规范](http://arxiv.org/abs/2602.23239v1) - arXiv
|
||||
- [InnerQ：大型语言模型的 KV 缓存的硬件感知免调优量化](http://arxiv.org/abs/2602.23200v1) - arXiv
|
||||
- [使用 Stylometry 辅助的 LLM 代理评估去匿名化风险](http://arxiv.org/abs/2602.23079v1) - arXiv
|
||||
- [拒绝混合：掩码令牌的快速语义传播以实现高效的 DLLM 推理](http://arxiv.org/abs/2602.22868v1) - arXiv
|
||||
- [通过超单纯形投影的可微零一损失](http://arxiv.org/abs/2602.23336v1) - arXiv
|
||||
- [FairQuant：用于医学图像分类的公平感知混合精度量化](http://arxiv.org/abs/2602.23192v1) - arXiv
|
||||
|
||||
---
|
||||
*Generated by AINewsCollector*
|
||||
|
||||
@ -16,6 +16,46 @@ const DAILY_DIR = path.join(__dirname, '../../daily');
|
||||
// 代理配置
|
||||
const PROXY_URL = process.env.HTTP_PROXY || process.env.HTTPS_PROXY || 'http://127.0.0.1:7890';
|
||||
|
||||
// 翻译缓存
|
||||
const translateCache = new Map();
|
||||
|
||||
// 使用 Google Translate API 翻译文本
|
||||
function translateToChinese(text) {
|
||||
if (!text || text.length === 0) return text;
|
||||
|
||||
// 检查缓存
|
||||
if (translateCache.has(text)) {
|
||||
return translateCache.get(text);
|
||||
}
|
||||
|
||||
try {
|
||||
const proxyFlag = PROXY_URL ? `--proxy "${PROXY_URL}"` : '';
|
||||
const encodedText = encodeURIComponent(text.slice(0, 500)); // 限制长度
|
||||
const url = `https://translate.googleapis.com/translate_a/single?client=gtx&sl=en&tl=zh-CN&dt=t&q=${encodedText}`;
|
||||
|
||||
const result = execSync(
|
||||
`curl -s ${proxyFlag} -L --max-time 10 "${url}"`,
|
||||
{ encoding: 'utf8', timeout: 15000 }
|
||||
);
|
||||
|
||||
const json = JSON.parse(result);
|
||||
// 解析翻译结果
|
||||
let translated = '';
|
||||
if (Array.isArray(json) && Array.isArray(json[0])) {
|
||||
for (const part of json[0]) {
|
||||
if (part && part[0]) translated += part[0];
|
||||
}
|
||||
}
|
||||
|
||||
const finalText = translated || text;
|
||||
translateCache.set(text, finalText);
|
||||
return finalText;
|
||||
} catch (err) {
|
||||
// 翻译失败，返回原文
|
||||
return text;
|
||||
}
|
||||
}
|
||||
|
||||
// 使用 curl 子进程请求（稳定支持代理）
|
||||
function fetch(url) {
|
||||
try {
|
||||
@ -178,8 +218,10 @@ function generateMarkdownZH(items, topCount, topics, date) {
|
||||
md += `## 🔥 Top ${topCount} 重要消息\n\n`;
|
||||
for (let i = 0; i < top10.length; i++) {
|
||||
const item = top10[i];
|
||||
md += `${i + 1}. [${item.title}](${item.url}) - **${item.source}**\n`;
|
||||
if (item.summary) md += ` > ${item.summary.slice(0, 150)}${item.summary.length > 150 ? '...' : ''}\n`;
|
||||
const titleZH = translateToChinese(item.title);
|
||||
const summaryZH = item.summary ? translateToChinese(item.summary.slice(0, 200)) : '';
|
||||
md += `${i + 1}. [${titleZH}](${item.url}) - **${item.source}**\n`;
|
||||
if (summaryZH) md += ` > ${summaryZH.slice(0, 150)}${summaryZH.length > 150 ? '...' : ''}\n`;
|
||||
md += '\n';
|
||||
}
|
||||
|
||||
@ -194,7 +236,8 @@ function generateMarkdownZH(items, topCount, topics, date) {
|
||||
if (topicItems.length > 0) {
|
||||
md += `### ${topic.name}\n\n`;
|
||||
for (const item of topicItems.slice(0, 10)) {
|
||||
md += `- [${item.title}](${item.url}) - ${item.source}\n`;
|
||||
const titleZH = translateToChinese(item.title);
|
||||
md += `- [${titleZH}](${item.url}) - ${item.source}\n`;
|
||||
}
|
||||
md += '\n';
|
||||
}
|
||||
@ -255,7 +298,10 @@ function generateMarkdown(items, topCount, topics) {
|
||||
year: 'numeric', month: '2-digit', day: '2-digit', timeZone: 'Asia/Shanghai'
|
||||
}).replace(/\//g, '-');
|
||||
|
||||
console.log('🌐 生成中文版（翻译中）...');
|
||||
const md_zh = generateMarkdownZH(items, topCount, topics, date);
|
||||
|
||||
console.log('🌐 生成英文版...');
|
||||
const md_en = generateMarkdownEN(items, topCount, topics, date);
|
||||
|
||||
return { md_zh, md_en, date };
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user