让智能体修复过程更高效，通过持续跟踪问题状态实现精准改进。
ADIAS: Automated Design of Interactive Agentic Systems
- 以问题为中心设计，用持久问题状态追踪修复进展
- 在五个基准上平均提升25.2%，四款模型均表现更优
- 适合需要持续迭代优化的交互式智能体开发场景
自动化智能体设计通过迭代修订、评估与反馈总结提升智能体性能。现有方法多为候选中心：跨轮次经验围绕候选智能体组织，导致修复进展隐含。这引发修复目标不明确、部分进展难积累、无效干预传播等问题。为此，本文提出以问题为中心的优化范式，将修复进展作为显式持久问题状态传递，而非每轮重新推导。我们构建了ADIAS框架，包含两项机制：持久问题状态维护问题身份、生命周期、证据及干预结果历史；问题引导优化则利用该状态联合提出修复目标与修改方向，实现聚焦的全代码修改。在五个交互式基准上，ADIAS平均优于最强基线25.2%，且在四款骨干模型上均取得一致提升。控制消融实验表明，移除持久问题状态或替换为候选中心策略，性能最高下降40.7%。
原文摘要 · Abstract (English)
Automated agent design improves agent harnesses through iterative revision, evaluation, and feedback summarization. Existing methods are largely candidate-centric: cross-round experience is organized around candidate agents, which leaves the repair progress implicit. This causes inefficient repair targeting, slow consolidation of partial progress, and propagation of ineffective interventions across rounds. Therefore, we formulate issue-centric agent optimization, in which repair progress is carried forward as an explicit persistent issue state to guide optimization, rather than re-derived from candidate history in each round. We instantiate the formulation in ADIAS, a framework for automated full-code agent design with two mechanisms. A persistent issue state maintains stable issue identities, lifecycle status, supporting evidence, and intervention-outcome histories. Issue-guided optimization uses this state to jointly propose repair targets and revision directions for subsequent focused full-code modification. Across five interactive benchmarks, ADIAS outperforms the strongest baseline by 25.2% on average and achieves consistent gains across four backbone models. Controlled ablations further show that removing persistent issue state or replacing issue-centric revision with candidate-centric policies leads to performance drops of up to 40.7%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。