| name | arex-towards-a-recursively-self-improving-agent-for |
| description | AREX: Towards a Recursively Self-Improving Agent for Deep Research |
| metadata | {"arxiv_id":"2607.21461","utility":1,"date_added":"2026-07-26"} |
AREX: Towards a Recursively Self-Improving Agent for Deep Research
arXiv: 2607.21461
Published: 2026-07-23
Utility: 1.0
Summary
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into tractable constraint-wise checks. This discovery--verification asymmetry suggests that a research agent should do more than simply search longer: it should recursively improve its current answer by verifying intermediate results and using the partially verified state to guide subsequent refinement. We introduce AREX, a family of Recursively Self-Improving (RSI) deep research agents. AREX alternates between an inner research loop that gathers evidence and constructs a provisional answer, and an outer self-improvement loop that audits the answer constraint-wise, identifies unresolved claims, and launches targeted follow-up research. To sustain RSI over long horizons, AREX learns an autonomous context-update tool that compresses growing interaction history into a compact improvement state preserving verified evidence and unresolved constraints, without relying on an external model. We train AREX on verified synthetic tasks and high-quality trajectories through agentic mid-training and long-horizon reinforcement learning. To mitigate sparse final rewards during long horizon learning, we emphasize key steps where decisive evidence is acquired or erroneous research directions are corrected. We instantiate a dense 4B model and a 122B-A10B Mixture-of-Experts model. Across BrowseComp, WideSearch, DeepSea...
Key Information
- Title: AREX: Towards a Recursively Self-Improving Agent for Deep Research
- Authors: [Extract from entry]
- Primary Category: cs.AI
Potential Skill Application
This paper presents research relevant to AI agent systems. Consider extracting methodologies, algorithms, or frameworks for skill development.
Reference
