AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/VectorSpaceLab/AREX-2
Sources
- Reinforced Self-Training (ReST) for Language Modeling
- DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
- R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
- AIDE: AI-Driven Exploration in the Space of Code
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- AREX: Towards a Recursively Self-Improving Agent for Deep Research
- FrontierCS: Evolving Challenges for Evolving Intelligence
- GAIA: a benchmark for General AI Assistants
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Humanity's Last Exam
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
- SWE-smith: Scaling Data for Software Engineering Agents
- Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
- Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems