Тёмный

NEW AGENTLESS AI Software Development 

code_your_own_AI
Подписаться 38 тыс.
Просмотров 2,5 тыс.
50% 1

A new leader for open-source software development: AGENTLESS. Best in class according to performance metrics on the SWE-bench Lite benchmark, including other open source agents w/ GPT-4 omni and Claude 3.5, like Aider or Devon or SWE-Agent.
AGENTLESS challenges the prevailing notion that complex autonomous agents are necessary for automating software development tasks. It leverages a simplified two-phase process-localization and repair-without the need for agents to decide on future actions or manage complex tools. This simplicity not only reduces the cognitive load involved in understanding and debugging the process but also significantly lowers operational costs. The empirical results demonstrate that AGENTLESS achieves competitive performance metrics on the SWE-bench Lite benchmark, outperforming all other open-source approaches in both effectiveness and efficiency.
The insights from AGENTLESS's performance suggest a paradigm shift in the development of software engineering tools, emphasizing the effectiveness of simpler, more interpretable methods over complex autonomous systems. This approach not only makes it easier to understand and maintain the system but also highlights the potential for significant cost savings and efficiency improvements. The research encourages further exploration into refining these simplistic approaches, suggesting that future advancements could focus on enhancing the accuracy of localization and repair mechanisms and exploring new forms of integration with existing development environments.
All rights w/ authors:
AGENTLESS :
Demystifying LLM-based Software Engineering Agents
arxiv.org/pdf/2407.01489
#airesearch
#newtech
#science

Наука

Опубликовано:

 

10 июл 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 12   
@joehopfield
@joehopfield 25 дней назад
In software engineering class at UCLA (1977) we submitted "PL/C" jobs on punch cards. Intended for teaching, PL/C implemented IBM's PL/1 but "fixed" syntax and a few logic errors for you. Any error became many pages of errors created by PL/C's attempted fixes. So we're nearly back to 50 years ago. 😀
@code4AI
@code4AI 24 дня назад
Thanks for this insight. It proves, that we are trying everything we know to make the machines a little bit more ..... clever ? For sure it is not intelligent.
@saulinfinite
@saulinfinite 26 дней назад
Amazing stuff! Keep it coming.
@preston_is_on_youtube
@preston_is_on_youtube 26 дней назад
Praise the Lord ☀️ for these sweet drops 🍭 of youtube manna 😭😭😭
@thesimplicitylifestyle
@thesimplicitylifestyle 26 дней назад
😎🤖
@propeacemindfortress
@propeacemindfortress 26 дней назад
when less is more... the we need more recommendations with less... errr.... passt scho^^
@spkgyk
@spkgyk 26 дней назад
The fact that companies are selling something that only works 20% of the time is crazy to me
@code4AI
@code4AI 24 дня назад
State of the art. Of course only in scientific terms, because if you look at some marketing statement: 104% and more .... smile.
@vladrm1
@vladrm1 24 дня назад
If it saves 5% or more effort in a team of 20+ devs, that's already more than 1 FTE so it could be useful.
@atomobianco
@atomobianco 24 дня назад
Agentless? To me it seems to operate in agentic mode, with multiple steps and LLM requests
@code4AI
@code4AI 24 дня назад
Ah, I understand. If you want to learn about agentic, and why this here is AGENTLESS; I have a dedicated video on what it means to be AGENTIC: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-yJHdxYJgYhg.html
Далее
On-Device: Functional Tokens (Octopus v2)
26:07
Просмотров 3,1 тыс.
GraphRAG or SpeculativeRAG ?
25:51
Просмотров 6 тыс.
Это реально работает?!
00:33
Просмотров 3 млн
СМОТРИМ YOUTUBE В МАЙНКРАФТЕ
00:34
Просмотров 977 тыс.
NEW TextGrad by Stanford: Better than DSPy
41:25
Просмотров 11 тыс.
5 Craziest AI Agents We've Ever Built
12:05
Просмотров 20 тыс.
Domain Shift solved: Predicted Reward Fine-Tuning
15:40
5 Easy Ways to help LLMs to Reason
50:37
Просмотров 4,4 тыс.
Masterclass on AI by Microsoft
20:50
Просмотров 1,6 тыс.
What are AI Agents?
12:29
Просмотров 121 тыс.
КРАХ WINDOWS 19 ИЮЛЯ 2024 | ОБЪЯСНЯЕМ
10:04
iPhone socket cleaning #Fixit
0:30
Просмотров 18 млн
КРАХ WINDOWS 19 ИЮЛЯ 2024 | ОБЪЯСНЯЕМ
10:04