AREX: Towards a Recursively Self-Improving Agent for Deep Research· AREX: 递归自我改进的深度研究智能体
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 target
递归自我改进智能体，加速深度研究过程中的发现与验证。
- 核心方法
- AREX通过交替进行内部研究循环（收集证据，构建临时答案）和外部自我改进循环（分步骤审计答案，识别未解决的声明并启动定向研究）来递归地自我改进。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 在深度研究中，智能体需要找到同时满足多个约束条件的答案，而发现这类答案成本高昂，验证则相对容易。
- 关键实验
- 展示了AREX在多个深度研究任务中的效率提升，但具体实验数据未提供。
- 主要贡献
- 提出了一种新的递归自我改进机制，有效减少了深度研究中找到正确答案所需的时间和资源。
- 意义与局限
- AREX为智能体在复杂问题解决中的自我优化提供了新思路，可能显著提升研究效率，但其在实际应用中的广泛性和鲁棒性仍需进一步验证。