AREX: Towards a Recursively Self-Improving Agent for Deep Research

arXiv:2607.21461 · cs.AI · Submitted 2026-07-23 · Read on arXiv

cs.AI

Submitted: 2026-07-23

Updated: 2026-09-01

Project page: https://vectorspacelab.github.io/arex-model

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 25× in this paper · explained in 2 episodes
• Benchmark — 16× in this paper · explained in 2 episodes
• Reinforcement Learning — 15× in this paper · explained in 4 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Ablation — 8× in this paper · explained in 1 episode
• Distillation — 7× in this paper · explained in 2 episodes
• Recursively Self-Improving — 7× in this paper
• Self-Distillation — 7× in this paper · explained in 7 episodes
• Autonomous Context Updating — 4× in this paper
• Agentic Task — 3× in this paper · explained in 1 episode
• Credit assignment — 3× in this paper · explained in 3 episodes
• GRPO — 3× in this paper · explained in 6 episodes
• Provenance — 3× in this paper · explained in 4 episodes
• Agentic Tasks — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Reward Shaping — 2× in this paper · explained in 2 episodes
• Test-time Scaling — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Agentic Search — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Beijing Academy of Artificial Intelligence — 1× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• State Management — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Humanity's Last Exam
• DeepSeek-V3 Technical Report
• DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
• Deep Research Agents: A Systematic Examination And Roadmap
• Mixtral of Experts
• WebSailor: Navigating Super-human Reasoning for Web Agent
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
• Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
• Mind DeepResearch Technical Report
• WebGPT: Browser-assisted question-answering with human feedback
• MemGPT: Towards LLMs as Operating Systems
• MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
• Tongyi DeepResearch Technical Report
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
• Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design
• Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection