AREX
Recursively self-improving research agent with constraint-wise verification
About
AREX is an academic research agent that leverages discovery-verification asymmetry to recursively improve answers to complex research questions. It systematically verifies solutions against multiple constraints and refines them through guided iterations, making it ideal for deep research tasks where answers must satisfy numerous requirements simultaneously. Published as open research, it demonstrates a novel approach to automated reasoning and constraint satisfaction in AI systems.
Details
| Type | coding-agent |
| Deployment | self-hosted |
| Supported Models |
Tags
Quick Info
- Organization
- Research Community
- Pricing
- open-source
- Free Tier
- Yes
- Updated
- Jul 24, 2026
Also in Agents
AI Data Analysis Agent
Autonomous agent that analyzes datasets and generates visual insights
AI Deep Research Agent
Autonomous agent that conducts comprehensive multi-source research investigations
AI Journalist Agent
Autonomous agent that researches topics and writes structured news articles