#textgrad search results

(8/8) Finally, my gratitude to the #TextGrad project (github.com/zou-group/text…) is beyond words — without the foundation it provided, this research simply wouldn’t exist.

(1/8) Existing LLM optimizers such as #TextGrad, #DSPy, and #LangChain are often too broad, which can make them inefficient at times. Also, it's difficult to combine the strengths of different optimizers.

Introducing #metaTextGrad🌟: a meta-optimization framework built on #TextGrad , designed to improve existing LLM optimizers by aligning them more closely with specific tasks. 📰 NeurIPS 2025 paper: openreview.net/pdf?id=10s01Yr… 🧑‍💻Code: github.com/zou-group/meta… 📚 Slides:…

2/4TextGrad 提出“文本微分”框架：将每次 LLM 反馈视为“梯度”，在计算图中自上而下传播。针对代码片段、提示、分子结构等变量，TextGrad 通过自然语言批评指导修改，实现类似反向传播的效果。 #TextGrad #微分范式

Here's the non-paywall version of our #TextGrad Nature paper rdcu.be/efRp4! 📜

I had a lot of fun discussing #textgrad on the @Nature podcast! It starts at around 12 minutes here nature.com/articles/d4158…

🚀 I’m thrilled to announce that #textgrad has been published in @Nature today! It’s been an incredible journey working with the TextGrad team, I am grateful for the wonderful collaboration within the Zou Group. @james_y_zou. 🙌 #Nature #AI #LLMs #AgenticAI

🚀 Thrilled to share that #textgrad is published in @Nature today! 🎉 It’s been an incredible journey working with the amazing TextGrad team and the Zou Group @james_y_zou. 🙌 ✨ What is TextGrad? A groundbreaking framework that automates optimization of LLMs and compound…

💡The key idea of #textgrad is to optimize by backpropagating textual gradients produced by #LLM. Paper: nature.com/articles/s4158… Code: github.com/zou-group/text… Amazing job by @mertyuksekgonul leading this project w/ fantastic collaborators @federicobianchy Joseph Boen @ShengLiu_…

⚡️Really thrilled that #textgrad is published in @nature today!⚡️ We present a general method for genAI to self-improve via our new *calculus of text*. We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!

🚀 The Future is Multi-LLM-based AI Systems🚀 In the upcoming multi-LLM systems, there’s a BIG question on the horizon: 𝗛𝗼𝘄 𝗱𝗼 𝘄𝗲 𝗘𝗩𝗔𝗟𝗨𝗔𝗧𝗘 𝘁𝗵𝗲𝘀𝗲 𝗔𝗜 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗱𝘂𝗿𝗶𝗻𝗴 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲? (as in #TextGrad @mertyuksekgonul @james_y_zou)

A while ago I wrote a thread about #TextGrad, which is an alternative prompt optimization method, based on "natural language gradients". Cool! Since we are still waiting for @karpathy's video reimplementing this from scratch... I thought I had to make my own... So here is the…

#TextGrad #LLM framework shows that optimizing answer AND the #PROMPT using multistep #reflextion, greatly improves accuracy. they created a python package with a similar syntax as pytorch. the framework has nice logging but I don't find it intuitive and extendable.

🔥Very cool application of #textgrad to reduce hallucination of visual-language #AI! Significantly increases reliability of GPT-4v/o.

🚀 #TextGrad is advancing multimodal reasoning and reducing hallucinations! Join us in contributing to TextGrad, an innovative framework that automatically optimizes foundation models via natural language gradients! Check it out here: github.com/zou-group/text…! 🌟

⚡️#TextGrad reduces hallucination in multimodal LLMs! MMVP 🏆 (multiple choice questions) - TextGrad optimized prompts increase the accuracy of GPT-4v from 71% -> 76%! HQH - Relation📍(open-ended generation) - TextGrad boosts the accuracy of GPT-4o from 77.2% to 82.5%!

It was a lot of fun talking about #TextGrad and mixture-of-agents at @agihouse_org!

A new blog update with TextGrad. Just do the small modification, and you can try other models like Yi-vision to work with TextGrad on Multimodal work. Welcome to communicate! #TextGrad #LLMs dylandigitalgarden.com/2024/July/July…

8/10 🛠️ TextGrad offers a flexible framework for optimizing text pipelines, similar to how PyTorch revolutionized neural networks. Your AI just got a lot smarter! 🧠 #AI #MachineLearning #TextGrad #Innovation

5/10 🎯 With TextGrad, we achieved state-of-the-art performance in PhD-level question answering (GPQA) and solved challenging LeetCode problems! 🚀 #AI #TextGrad #Innovation #MachineLearning

Introducing #metaTextGrad🌟: a meta-optimization framework built on #TextGrad , designed to improve existing LLM optimizers by aligning them more closely with specific tasks. 📰 NeurIPS 2025 paper: openreview.net/pdf?id=10s01Yr… 🧑‍💻Code: github.com/zou-group/meta… 📚 Slides:…

(1/8) Existing LLM optimizers such as #TextGrad, #DSPy, and #LangChain are often too broad, which can make them inefficient at times. Also, it's difficult to combine the strengths of different optimizers.

⚡️This is the most fun project! We built PyTorch-for-text! 🔥 #TextGrad: automated "differentiation" via text to optimize AI systems by backpropagating LLM text feedback. TextGrad + GPT4o: 💻LeetCodeHard best score ❓GPQA sota 🧬Designs new molecules 🩺Improves treatments 🧵

⚡️Really thrilled that #textgrad is published in @nature today!⚡️ We present a general method for genAI to self-improve via our new *calculus of text*. We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!

#TextGrad now features multimodal reasoning! 🔬 ScienceQA (multimodal scientific reasoning) - Error rate drops by 20%, achieving the highest zero-shot performance we know of. 📊 MathVista (multimodal math reasoning) - Boosting the score from 63.8% to 66.1% on GPT-4o! Explore…

#TextGrad #LLM framework shows that optimizing answer AND the #PROMPT using multistep #reflextion, greatly improves accuracy. they created a python package with a similar syntax as pytorch. the framework has nice logging but I don't find it intuitive and extendable.

A while ago I wrote a thread about #TextGrad, which is an alternative prompt optimization method, based on "natural language gradients". Cool! Since we are still waiting for @karpathy's video reimplementing this from scratch... I thought I had to make my own... So here is the…

5/n #TextGrad can optimize prompts, but it's much more than that! For example, we used it to optimize code solutions to achieve the highest reported scores on LeetCodeHard.

🚀 The Future is Multi-LLM-based AI Systems🚀 In the upcoming multi-LLM systems, there’s a BIG question on the horizon: 𝗛𝗼𝘄 𝗱𝗼 𝘄𝗲 𝗘𝗩𝗔𝗟𝗨𝗔𝗧𝗘 𝘁𝗵𝗲𝘀𝗲 𝗔𝗜 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗱𝘂𝗿𝗶𝗻𝗴 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲? (as in #TextGrad @mertyuksekgonul @james_y_zou)

Discover #TextGrad! Optimize AI systems with text feedback from LLMs. From code to drug discovery, it's all possible with a few lines of code! 🚀 #RapidInnovation #AI #MachineLearning

⚡️#TextGrad reduces hallucination in multimodal LLMs! MMVP 🏆 (multiple choice questions) - TextGrad optimized prompts increase the accuracy of GPT-4v from 71% -> 76%! HQH - Relation📍(open-ended generation) - TextGrad boosts the accuracy of GPT-4o from 77.2% to 82.5%!