# LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking

arXiv: https://arxiv.org/abs/2406.14917 · HTML: https://mlsanity.com/paper/2406.14917/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 21 Jun 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery](https://mlsanity.com/paper/2302.03668/) (2023)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [Large Language Models as Evolutionary Optimizers](https://mlsanity.com/paper/2310.19046/) (2023)
- [Language Model Crossover: Variation through Few-Shot Prompting](https://mlsanity.com/paper/2302.12170/) (2023)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [Black-box Prompt Learning for Pre-trained Language Models](https://mlsanity.com/paper/2201.08531/) (2022)
- [A Survey on Large Language Model Hallucination via a Creativity Perspective](https://mlsanity.com/paper/2402.06647/) (2024)
- [AI Hallucinations: A Misnomer Worth Clarifying](https://mlsanity.com/paper/2401.06796/) (2024)
- [Large Language Model for Multi-objective Evolutionary Optimization](https://mlsanity.com/paper/2310.12541/) (2023)
- [Prompt Evolution for Generative AI: A Classifier-Guided Approach](https://mlsanity.com/paper/2305.16347/) (2023)
- [SARD: A Human-AI Collaborative Story Generation](https://mlsanity.com/paper/2403.01575/) (2024)
- [Large Language and Text-to-3D Models for Engineering Design Optimization](https://mlsanity.com/paper/2307.01230/) (2023)
- [Generative AI-based Prompt Evolution Engineering Design Optimization With Vision-Language Model](https://mlsanity.com/paper/2406.09143/) (2024)

## Built on by (most cited first, 2 of 2)

- [From Idea to CAD: A Language Model-Driven Multi-Agent System for Collaborative Design](https://mlsanity.com/paper/2503.04417/) (2025)
- [The Variance Paradox: How AI Reduces Diversity but Increases Novelty](https://mlsanity.com/paper/2508.19264/) (2025)

## Abstract (arXiv)

This paper presents LLM2TEA, a Large Language Model (LLM) driven MultiTask Evolutionary Algorithm, representing the first agentic AI designer of its kind operating with generative evolutionary multitasking (GEM). LLM2TEA enables the crossbreeding of solutions from multiple domains, fostering novel solutions that transcend disciplinary boundaries. Of particular interest is the ability to discover designs that are both novel and conforming to real-world physical specifications. LLM2TEA comprises an LLM to generate genotype samples from text prompts describing target objects, a text-to-3D generative model to produce corresponding phenotypes, a classifier to interpret its semantic representations, and a computational simulator to assess its physical properties. Novel LLM-based multitask evolutionary operators are introduced to guide the search towards high-performing, practically viable designs. Experimental results in conceptual design optimization validate the effectiveness of LLM2TEA, showing 97% to 174% improvements in the diversity of novel designs over the current text-to-3D baseline. Moreover, over 73% of the generated designs outperform the top 1% of designs produced by the text-to-3D baseline in terms of physical performance. The designs produced by LLM2TEA are not only aesthetically creative but also functional in real-world contexts. Several of these designs have been successfully 3D printed, demonstrating the ability of our approach to transform AI-generated outputs into tangible, physical designs. These designs underscore the potential of LLM2TEA as a powerful tool for complex design optimization and discovery, capable of producing novel and physically viable designs.