Image de couverture de livre

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Keren, Tomer, Calderon, Nitay, Yehudai, Asaf, Perlitz, Yotam, Shmueli-Scheuer, Michal, Reichert, Roi
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
par: Yehudai, Asaf, et autres
Publié: (2025)

Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
par: Yehudai, Asaf, et autres
Publié: (2026)

General Agent Evaluation
par: Bandel, Elron, et autres
Publié: (2026)

JuStRank: Benchmarking LLM Judges for System Ranking
par: Gera, Ariel, et autres
Publié: (2024)

Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench
par: Perlitz, Yotam, et autres
Publié: (2024)

Growing Pains: Extensible and Efficient LLM Benchmarking Via Fixed Parameter Calibration
par: Habba, Eliya, et autres
Publié: (2026)

Survey on Evaluation of LLM-based Agents
par: Yehudai, Asaf, et autres
Publié: (2025)

On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs
par: Calderon, Nitay, et autres
Publié: (2024)

Efficient Benchmarking of Language Models
par: Perlitz, Yotam, et autres
Publié: (2023)

LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
par: Toker, Gilat, et autres
Publié: (2026)

ELT-Bench-Verified: Benchmark Quality Issues Underestimate AI Agent Capabilities
par: Zanoli, Christopher, et autres
Publié: (2026)

The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs
par: Calderon, Nitay, et autres
Publié: (2025)

The Mighty ToRR: A Benchmark for Table Reasoning and Robustness
par: Ashury-Tahan, Shir, et autres
Publié: (2025)

Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI
par: Bandel, Elron, et autres
Publié: (2024)

Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
par: Kour, George, et autres
Publié: (2025)

CUBE: A Standard for Unifying Agent Benchmarks
par: Lacoste, Alexandre, et autres
Publié: (2026)

When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes
par: Yehudai, Asaf, et autres
Publié: (2024)

Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
par: Yehudai, Asaf, et autres
Publié: (2026)

The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth
par: Lissak, Shir, et autres
Publié: (2024)

ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models
par: Ashury-Tahan, Shir, et autres
Publié: (2026)

Robustness as an Emergent Property of Task Performance
par: Ashury-Tahan, Shir, et autres
Publié: (2026)

NL-Eye: Abductive NLI for Images
par: Ventura, Mor, et autres
Publié: (2024)

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
par: Wang, Leyao, et autres
Publié: (2026)

WildIFEval: Instruction Following in the Wild
par: Lior, Gili, et autres
Publié: (2025)

DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation
par: Habba, Eliya, et autres
Publié: (2025)

How Safe is Your Safety Metric? Automatic Concatenation Tests for Metric Reliability
par: Fandina, Ora Nova, et autres
Publié: (2024)

Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models
par: Gupta, Sonam, et autres
Publié: (2024)

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking
par: Kazoom, Roie, et autres
Publié: (2026)

A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns
par: Yehudai, Asaf, et autres
Publié: (2024)

Interactive Explanations for Reinforcement-Learning Agents
par: Amitai, Yotam, et autres
Publié: (2025)

Can We Govern the Agent-to-Agent Economy?
par: Chaffer, Tomer Jordi
Publié: (2025)

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation
par: Kaplan, Erel, et autres
Publié: (2026)

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning
par: Wang, Xukai, et autres
Publié: (2025)

Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
par: Calderon, Nitay, et autres
Publié: (2026)

Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications
par: Halfon, Alon, et autres
Publié: (2024)

Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
par: Gerstgrasser, Matthias, et autres
Publié: (2023)

Workflows vs Agents for Code Translation
par: Gray, Henry, et autres
Publié: (2025)

Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants
par: Cherny-Shahar, Tsvi, et autres
Publié: (2026)

All You Need is Sally-Anne: ToM in AI Strongly Supported After Surpassing Tests for 3-Year-Olds
par: Alon, Nitay, et autres
Publié: (2025)

TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design
par: Zhu, Haonan, et autres
Publié: (2026)