Cover Image

What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Audran-Reiss, Alexis, Armengol-Estapé, Jordi, Hambardzumyan, Karen, Budhiraja, Amar, Josifoski, Martin, Toledo, Edan, Hazra, Rishi, Magka, Despoina, Shvartsman, Michael, Pathak, Parth, Kao, Justine T, Cipolina-Kun, Lucia, Gauri, Bhavul, Gagnon-Audet, Jean-Christophe, Tewolde, Emanuel, Zhang, Jenny, Cohen, Taco, Adi, Yossi, Shavrina, Tatiana, Bachrach, Yoram
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
by: Maiti, Shalini, et al.
Published: (2025)

AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents
by: Lupidi, Alisia, et al.
Published: (2026)

AIRA_2: Overcoming Bottlenecks in AI Research Agents
by: Hambardzumyan, Karen, et al.
Published: (2026)

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
by: Toledo, Edan, et al.
Published: (2025)

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
by: Zhao, Bingchen, et al.
Published: (2025)

APRES: An Agentic Paper Revision and Evaluation System
by: Zhao, Bingchen, et al.
Published: (2026)

Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
by: Pepe, Alberto, et al.
Published: (2026)

MLGym: A New Framework and Benchmark for Advancing AI Research Agents
by: Nathani, Deepak, et al.
Published: (2025)

Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting
by: Javaji, Shashidhar Reddy, et al.
Published: (2025)

Bootstrapping Task Spaces for Self-Improvement
by: Jiang, Minqi, et al.
Published: (2025)

Scaling and Distilling Transformer Models for sEMG
by: Mehlman, Nicholas, et al.
Published: (2025)

Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations
by: Thöni, Anna C. M., et al.
Published: (2025)

LLMs versus the Halting Problem: Characterizing Program Termination Reasoning
by: Sultan, Oren, et al.
Published: (2026)

Diverse AI Personas Can Mitigate the Homogenization Effect in Human-AI Collaborative Ideation
by: Wan, Yun, et al.
Published: (2025)

A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs
by: Kalra, Dayal Singh, et al.
Published: (2026)

Scaling Small Agents Through Strategy Auctions
by: Alazraki, Lisa, et al.
Published: (2026)

Crowd IQ -- Aggregating Opinions to Boost Performance
by: Kosinski, Michal, et al.
Published: (2024)

SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly
by: Armengol-Estapé, Jordi, et al.
Published: (2023)

Social Financing Alternatives for Social Economy Enterprises: Coop57
by: Glòria Estapé-Dubreuil
Published: (2014)

From MTEB to MTOB: Retrieval-Augmented Classification for Descriptive Grammars
by: Kornilov, Albert, et al.
Published: (2024)

On Some Extensions of the Boué-Dupuis Variational Formula
by: Budhiraja, A.
Published: (2024)

Las actividades productivas y su relación con la contaminación del agua de la Microcuenca Negroyacu, en Guaranda, Ecuador
by: Carlos Taco-Taco
Published: (2017)

The Finiteness Principle for the boundary values of $C^2$-functions
by: Shvartsman, Pavel
Published: (2024)

Efficient Algorithms for Lipschitz Selections of Set-Valued Mappings in ${\bf R}^2$: long version
by: Shvartsman, Pavel
Published: (2025)

Mind the Web: The Security of Web Use Agents
by: Shapira, Avishag, et al.
Published: (2025)

DPs, Phi-features and Tense in the Context of Abyssinian (Eritrean and Ethiopian) Semitic Languages
by: Tewolde, Tesfay
Published: (2022)

julieaudet/cell-manufacturing: HDDE
by: Julie Audet
Published: (2026)

GIS in schools / Richard Audet and Gail Ludwig
by: Audet, Richard

Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
by: Jiralerspong, Marco, et al.
Published: (2023)

Modelling Chemical Reaction Networks using Neural Ordinary Differential Equations
by: Thöni, Anna C. M., et al.
Published: (2025)

Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs
by: Cummins, Chris, et al.
Published: (2024)

DUAS FACES DO PODER
by: Peter Bachrach
Published: (2011)

Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play
by: Cipolina-Kun, Lucia, et al.
Published: (2025)

Asking the Right Questions: Improving Reasoning with Generated Stepping Stones
by: Hu, Hengyuan, et al.
Published: (2026)

Irreducibility and locus of complex roots of polynomials related to Fermat's Last Theorem
by: Karapetyan, Hayk, et al.
Published: (2025)

On ideal class groups of totally degenerate number rings
by: Hambardzumyan, Ruben, et al.
Published: (2025)

Graphs, Disjoint Matchings and Some Inequalities
by: Hambardzumyan, Lianna, et al.
Published: (2015)

Real Time Fatigue Crack Growth Monitoring Using High Precision Control and Data Acquisition Systems
by: Hambardzumyan, Arev, et al.
Published: (2025)

Training AI Co-Scientists Using Rubric Rewards
by: Goel, Shashwat, et al.
Published: (2025)

Constructing surfaces with first Steklov eigenvalue of arbitrarily large multiplicity
by: Audet-Beaumont, Samuel
Published: (2024)