Agent evaluation
Agent evaluation is the systematic measurement of how well AI agents (LLM-based systems that plan and act over multiple steps using tools) perform on real-world tasks, using benchmarks, metrics, and testing…
AI Agents
Explore AI Agents through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Model Evaluation
Articles that also belong to these categories. Counts cover all of AI Agents.
All articles (272)Developer Tools (78)Open Source AI (53)AI Companies (51)AI Tools & Products (47)AI Code Generation (34)AI Benchmarks (28)ChatGPT (28)Large Language Models (22)Artificial Intelligence (19)OpenAI (19)Anthropic (14)Enterprise AI (14)Machine Learning (12)Chinese AI (10)AI Research (9)AI Infrastructure (8)AI Models (8)Information Retrieval (8)AI Safety (7)Meta AI (7)Multimodal AI (7)NVIDIA (7)Conversational AI (6)Generative AI (6)Google (6)Microsoft (6)Model Evaluation (6)AI for Science (5)Google DeepMind (5)Natural Language Processing (5)Reinforcement Learning (5)Software Development (5)AI in Gaming (4)Reasoning Models (4)Robotics (4)Voice AI (4)Prompt Engineering (3)Agentic Commerce (2)Finance AI (2)Healthcare AI (2)Mathematics (2)AI Alignment (1)AI Incidents & Controversies (1)AI Policy & Regulation (1)China AI (1)Computer Science (1)Computer Vision (1)Legal AI (1)Mixture of Experts (1)People (1)Programming Languages (1)Robotics Companies (1)Speech & Audio AI (1)Training & Optimization (1)World Models (1)
Showing 1-6 of 6 articles
Harness (AI)
Harness, in artificial intelligence, is the software scaffolding that wraps a machine learning model, most often a large language model
SkillEvaluator
SkillEvaluator is an open-source command-line framework developed by NVIDIA for evaluating artifacts used by AI agents.
Terminal-Bench
Terminal-Bench is an open benchmark for evaluating AI agents on complex, real-world tasks performed through command-line terminal interfaces.
WebArena
WebArena is a realistic, self-hosted web environment and benchmark designed for developing and evaluating autonomous AI agents that perform tasks on the web.
WebVoyager
WebVoyager is an end-to-end web agent and its companion benchmark, introduced by Hongliang He and seven coauthors in a paper accepted to ACL 2024 .