LogoThread Easy
  • Explorar
  • Criar thread
LogoThread Easy

Seu parceiro completo para threads do Twitter

© 2025 Thread Easy All Rights Reserved.

Explorar

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

最近通过对抗来提升智能体效果的论文层出不穷,这又来了一篇关于代码补丁的多智能体(multi-agents)论文! 声称在SWE-bench Verified排行榜上达到了SOTA(79.4%)。

它可以通过自动化错误修复快速改进提升代码质量。

方法也简单,以前自动化测试只能照顾到我们想象到的case,但很难照顾到边缘case。

于是就构建一个测试用例考官,专门来出题去测试打补丁的agent。

这就是这项新研究引入的InfCode,这是一个框架,测试和补丁通过对抗性迭代相互挑战。

将测试生成和补丁创建视为对立的力量。

测试试图破坏补丁。

补丁不断发展以便通过测试。

两者都在冲突中变得更强大。

不断改进补丁以处理这些故障。

又开始生成更难的测试。

重复此操作,直到补丁变得健壮。

它们不仅仅通过在修复存在之前设计的测试。

而是不断发现边缘case得以强化。

在SWE-Bench Verified上进行评估,该方法在补丁质量和覆盖率方面显示出可衡量的提升。

减少了回归,并实现了更强大的修复。

论文链接:

最近通过对抗来提升智能体效果的论文层出不穷,这又来了一篇关于代码补丁的多智能体(multi-agents)论文! 声称在SWE-bench Verified排行榜上达到了SOTA(79.4%)。 它可以通过自动化错误修复快速改进提升代码质量。 方法也简单,以前自动化测试只能照顾到我们想象到的case,但很难照顾到边缘case。 于是就构建一个测试用例考官,专门来出题去测试打补丁的agent。 这就是这项新研究引入的InfCode,这是一个框架,测试和补丁通过对抗性迭代相互挑战。 将测试生成和补丁创建视为对立的力量。 测试试图破坏补丁。 补丁不断发展以便通过测试。 两者都在冲突中变得更强大。 不断改进补丁以处理这些故障。 又开始生成更难的测试。 重复此操作,直到补丁变得健壮。 它们不仅仅通过在修复存在之前设计的测试。 而是不断发现边缘case得以强化。 在SWE-Bench Verified上进行评估,该方法在补丁质量和覆盖率方面显示出可衡量的提升。 减少了回归,并实现了更强大的修复。 论文链接:

转载自 @omarsar0

avatar for Yangyi
Yangyi
Wed Nov 26 17:19:51
RT @GregHBurnham: I looked into this and the answer is so funny. In the No Thinking setting, Opus 4.5 repurposes the Python tool to have an…

RT @GregHBurnham: I looked into this and the answer is so funny. In the No Thinking setting, Opus 4.5 repurposes the Python tool to have an…

research @cornell // language models, information theory, science of AI

avatar for dr. jack morris
dr. jack morris
Wed Nov 26 17:18:58
Auto-Autonomy: Cars Are Racing Toward Disruption 2014 (Waymo was just ~4 years in) https://t.co/OSQaUQMwPA

Auto-Autonomy: Cars Are Racing Toward Disruption 2014 (Waymo was just ~4 years in) https://t.co/OSQaUQMwPA

Subscribe https://t.co/Xm1OaUU8jk • seed investing • writing • ॐ •🙏• I use '—' • tweets saved 90 days • 📷

avatar for Steven Sinofsky
Steven Sinofsky
Wed Nov 26 17:17:25
以清晰的45°俯视视角,呈现城市地标的 3D Q版微缩场景,画面竖版(9:16)居中构图,建筑置于画面中央,突出微缩模型精准细致的立体美感。 画面材质细腻温润,体现真实的PBR质感与柔和逼真的光影效果。 

整体构图简洁干净、视觉统一,巧妙在城市建筑中融入天气元素,动态天气效果与城市景观融合互动,营造身临其境的天气视觉氛围。 

文字语言和输入的城市名称语言保持一致 背景选用纯色、柔和的色调,突出主体内容,整体风格清新舒适。 图片正上方显示醒目的代表天气的图标,图标下方是日期(超小字)、温度范围(中号),图标上方是城市名(大号) 天气信息无背景,可以和城市建筑重叠融合 

请联网获取输入的城市的当前天气信息后生成 

城市名称:【Chicago】

以清晰的45°俯视视角,呈现城市地标的 3D Q版微缩场景,画面竖版(9:16)居中构图,建筑置于画面中央,突出微缩模型精准细致的立体美感。 画面材质细腻温润,体现真实的PBR质感与柔和逼真的光影效果。 整体构图简洁干净、视觉统一,巧妙在城市建筑中融入天气元素,动态天气效果与城市景观融合互动,营造身临其境的天气视觉氛围。 文字语言和输入的城市名称语言保持一致 背景选用纯色、柔和的色调,突出主体内容,整体风格清新舒适。 图片正上方显示醒目的代表天气的图标,图标下方是日期(超小字)、温度范围(中号),图标上方是城市名(大号) 天气信息无背景,可以和城市建筑重叠融合 请联网获取输入的城市的当前天气信息后生成 城市名称:【Chicago】

Prompt Engineer, dedicated to learning and disseminating knowledge about AI, software engineering, and engineering management.

avatar for 宝玉
宝玉
Wed Nov 26 17:14:58
What happened to "energy is gdp" was industrial irrelevance of Saudi Arabia and Russia. Kilowatts are a more accurate metric of where things are going than joules, this isn't favoritism.

What happened to "energy is gdp" was industrial irrelevance of Saudi Arabia and Russia. Kilowatts are a more accurate metric of where things are going than joules, this isn't favoritism.

We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1

avatar for Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
Wed Nov 26 17:14:52
🍌 nano banana pro prompt (with gemini)

Dynamically generate a current weather card based on a given city name.

--- prompt ---

Present a clear, 45° top-down view of a vertical (9:16) isometric miniature 3D cartoon scene, highlighting iconic landmarks centered in the composition to showcase precise and delicate modeling.

The scene features soft, refined textures with realistic PBR materials and gentle, lifelike lighting and shadow effects. Weather elements are creatively integrated into the urban architecture, establishing a dynamic interaction between the city's landscape and atmospheric conditions, creating an immersive weather ambiance.

Use a clean, unified composition with minimalistic aesthetics and a soft, solid-colored background that highlights the main content. The overall visual style is fresh and soothing.

Display a prominent weather icon at the top-center, with the date (x-small text) and temperature range (medium text) beneath it. The city name (large text) is positioned directly above the weather icon. The weather information has no background and can subtly overlap with the buildings.

The text should match the input city's native language.
Please retrieve current weather conditions for the specified city before rendering.

City name:【上海】

🍌 nano banana pro prompt (with gemini) Dynamically generate a current weather card based on a given city name. --- prompt --- Present a clear, 45° top-down view of a vertical (9:16) isometric miniature 3D cartoon scene, highlighting iconic landmarks centered in the composition to showcase precise and delicate modeling. The scene features soft, refined textures with realistic PBR materials and gentle, lifelike lighting and shadow effects. Weather elements are creatively integrated into the urban architecture, establishing a dynamic interaction between the city's landscape and atmospheric conditions, creating an immersive weather ambiance. Use a clean, unified composition with minimalistic aesthetics and a soft, solid-colored background that highlights the main content. The overall visual style is fresh and soothing. Display a prominent weather icon at the top-center, with the date (x-small text) and temperature range (medium text) beneath it. The city name (large text) is positioned directly above the weather icon. The weather information has no background and can subtly overlap with the buildings. The text should match the input city's native language. Please retrieve current weather conditions for the specified city before rendering. City name:【上海】

以清晰的45°俯视视角,呈现城市地标的 3D Q版微缩场景,画面竖版(9:16)居中构图,建筑置于画面中央,突出微缩模型精准细致的立体美感。 画面材质细腻温润,体现真实的PBR质感与柔和逼真的光影效果。 整体构图简洁干净、视觉统一,巧妙在城市建筑中融入天气元素,动态天气效果与城市景观融合互动,营造身临其境的天气视觉氛围。 文字语言和输入的城市名称语言保持一致 背景选用纯色、柔和的色调,突出主体内容,整体风格清新舒适。 图片正上方显示醒目的代表天气的图标,图标下方是日期(超小字)、温度范围(中号),图标上方是城市名(大号) 天气信息无背景,可以和城市建筑重叠融合 请联网获取输入的城市的当前天气信息后生成 城市名称:【Chicago】

avatar for 宝玉
宝玉
Wed Nov 26 17:13:20
  • Previous
  • 1
  • More pages
  • 2287
  • 2288
  • 2289
  • More pages
  • 5635
  • Next