Book a Demo

AI Research
That Transforms
Industries

AI Research
That Transforms
Industries

AI Research
That Transforms
Industries

AlgoVerde Events

AlgoVerde Events

AlgoVerde Events

Check out our curated selection of GenAI papers

Every week our team explores all the relevant research in GenAI.

Every week our team explores all the relevant research in GenAI.

Latest Research on GenAI

Latest Research on GenAI

Latest Research
on GenAI

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

LLMs are capable of outstanding creative output, but are held back by the phenomenon called "mode collapse". Verbalized Sampling is a way to unlock the massive creative potential of LLMs, improving output diversity in tasks like creative writing, dialogue simulations and open-ended questions.

LLMs are capable of outstanding creative output, but are held back by the phenomenon called "mode collapse". Verbalized Sampling is a way to unlock the massive creative potential of LLMs, improving output diversity in tasks like creative writing, dialogue simulations and open-ended questions.

Northeastern, Stanford & West Virginia University

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

TUMIX transforms a single LLM into a powerful committee of diverse AI agents that collaborate using code and search to find superior solutions to complex problems.

TUMIX transforms a single LLM into a powerful committee of diverse AI agents that collaborate using code and search to find superior solutions to complex problems.

MIT, Harvard, Google

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

With ACE, the model writes, reflects, and edits its own prompt over and over until it becomes a self-improving system. Each failure becomes a strategy. Each success becomes a rule.

With ACE, the model writes, reflects, and edits its own prompt over and over until it becomes a self-improving system. Each failure becomes a strategy. Each success becomes a rule.

Q. Zhang, C. Hu, S. Upasani, B. Ma, F. Hong, V. Kamanuru, J. Rainton, C. Wu, M. Ji, H. Li, U. Thakker, J. Zou, K. Olukotun

LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings

LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings

LLMs can predict human survey responses with 90% reliability. What could be done in months and for thousands of dollars can now be done in days and in a much more scalable way.

LLMs can predict human survey responses with 90% reliability. What could be done in months and for thousands of dollars can now be done in days and in a much more scalable way.

PyMC Labs, Colgate

Evergreen Research on GenAI

Evergreen Research on GenAI

Evergreen Research on GenAI

Using LLMs for Market Research

AI tools will play a crucial role in understanding consumer behavior and preferences.

James Brand, Ayelet Israeli, Donald Ngwe

The Crowdless Future? Generative AI and Creative Problem Solving

GenAI is shaping the future of crowdsourcing.

Leonard Boussioux, Jacqueline N. Lane, Miaomiao Zhang, Vladimir Jacimovic, Karim R. Lakhani

Out of One, Many: Using Language Models to Simulate Human Samples

Using language models to simulate human samples.

Lisa P. Argyle, Ethan C. Busby, Nancy Fulda, Joshua Gubler, Christopher Rytting, David Wingate

Learning to Use the Bicycle for the Mind

Solving the knowing-doing gap with Generative AI.

Karim Lakhani

Navigating the Jagged Technological Frontier

AI boosts knowledge worker productivity.

Fabrizio Dell’Acqua, Edward McFowland III, Ethan Mollick, Hila Lifshitz-Assaf, Katherine C. Kellogg, Saran Rajendran Lisa Krayer, Francois Candelon, Karim R. Lakhani

Language Models that Think, Chat Better

Princeton researchers cracked the code for teaching AI to think like humans in everyday conversations (not just math problems) and their 8B model now outsmarts 150B+ parameter giants.

Adithya Bhaskar, Xi Ye, Danqi Chen

The Cybernetic Teammate

AI enhances individual performance to team levels, bridges functional silos, and fosters positive engagement, reshaping collaboration dynamics in knowledge work.

F. Dell’Acqua, C. Ayoubi, K. Lakhani

Generative AI and the Nature of Work

Recent advances in artificial intelligence (AI) technology demonstrate considerable potential to complement human capital intensive activities.

Manuel Hoffmann, Sam Boysel, Frank Nagle, Sida Peng, Kevin Xu

When Combinations of Humans and AI are Useful

A systematic review and meta-analysis.

Michelle Vaccaro, Abdullah Almaatouq, Thomas Malone

Using LLMs for Market Research

AI tools will play a crucial role in understanding consumer behavior and preferences.

James Brand, Ayelet Israeli, Donald Ngwe

The Crowdless Future? Generative AI and Creative Problem Solving

GenAI is shaping the future of crowdsourcing.

Leonard Boussioux, Jacqueline N. Lane, Miaomiao Zhang, Vladimir Jacimovic, Karim R. Lakhani

Out of One, Many: Using Language Models to Simulate Human Samples

Using language models to simulate human samples.

Lisa P. Argyle, Ethan C. Busby, Nancy Fulda, Joshua Gubler, Christopher Rytting, David Wingate

Learning to Use the Bicycle for the Mind

Solving the knowing-doing gap with Generative AI.

Karim Lakhani

Navigating the Jagged Technological Frontier

AI boosts knowledge worker productivity.

Fabrizio Dell’Acqua, Edward McFowland III, Ethan Mollick, Hila Lifshitz-Assaf, Katherine C. Kellogg, Saran Rajendran Lisa Krayer, Francois Candelon, Karim R. Lakhani

Language Models that Think, Chat Better

Princeton researchers cracked the code for teaching AI to think like humans in everyday conversations (not just math problems) and their 8B model now outsmarts 150B+ parameter giants.

Adithya Bhaskar, Xi Ye, Danqi Chen

The Cybernetic Teammate

AI enhances individual performance to team levels, bridges functional silos, and fosters positive engagement, reshaping collaboration dynamics in knowledge work.

F. Dell’Acqua, C. Ayoubi, K. Lakhani

Generative AI and the Nature of Work

Recent advances in artificial intelligence (AI) technology demonstrate considerable potential to complement human capital intensive activities.

Manuel Hoffmann, Sam Boysel, Frank Nagle, Sida Peng. Kevin Xu

When Combinations of Humans and AI are Useful

A systematic review and meta-analysis.

Michelle Vaccaro, Abdullah Almaatouq & Thomas Malone

Discover the Academic Research Underpinning AlgoVerde

Check out our new article "AI Redefines Consumer Sentiment Research in 2025" on Substack

Check out our new article "AI Redefines Consumer Sentiment Research in 2025" on Substack

Check out our new article "AI Redefines Consumer Sentiment Research in 2025" on Substack