AI Agents
An AI agent is a software system that selects and performs actions in an environment in pursuit of an objective.
AI Agents
Explore AI Agents through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Machine Learning
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 1-12 of 12 articles
Agentic Context Engineering
Agentic Context Engineering (ACE) is a framework for scalable and efficient context adaptation in large language models (LLMs) that lets an AI system improve itself by treating its own context as an evolving
Coconut (Chain of Continuous Thought)
Coconut (Chain of Continuous Thought) is a reasoning paradigm for large language models introduced by researchers at FAIR at Meta, Meta's Fundamental AI Research lab, and the University of California
Computer-use agent
A computer-use agent (CUA) is a category of AI agent in artificial intelligence that performs tasks by directly operating a general-purpose computer's graphical user interface (GUI) the way a human does, by…
Corrective RAG (CRAG)
Corrective Retrieval Augmented Generation (CRAG) is a method for improving the robustness of retrieval-augmented generation (RAG) when the underlying retrieval step returns irrelevant, incomplete, or factually…
Frontis-MA1
Frontis-MA1 is a family of open-weight large language models post-trained to act as agents for machine learning engineering (MLE), released in late July 2026 by FrontisAI
MemGPT
MemGPT (short for Memory-GPT) is a system and agent design pattern that gives large language model agents long-term memory by managing data between the model's bounded context window and external storage
Mixture of Agents
Mixture of Agents (MoA) is a multi-model collaboration framework that combines multiple large language models (LLMs) in a layered architecture
RAPTOR
RAPTOR (Recursive Abstractive Processing for Tree-Organized Retrieval) is a retrieval method for retrieval-augmented generation introduced in a 2024 paper by researchers at Stanford University.
Reflexion
Reflexion is a 2023 framework for reinforcing language agents through verbal self-reflection rather than weight updates: the agent reflects in natural language on feedback from failed attempts, stores those…
Self-RAG
Self-RAG (Self-Reflective Retrieval-Augmented Generation) is a framework that trains a single large language model to adaptively decide when to retrieve external passages, to generate text grounded in those…
Sleep-time compute
Sleep-time compute is a technique for large language model inference in which a model uses idle periods, before any user query has arrived, to "think" about a known context offline and pre-compute a richer…