让多个智能体并行研究，解决长文本任务中的信息干扰问题。
Self-Manager: Parallel Agent Loop for Long-form Deep Research
- 用独立线程池实现多智能体异步并行，避免上下文冲突。
- 在DeepResearch Bench上所有指标均优于单线程基线模型。
- 适合需要深度、长时程研究的复杂任务，如学术综述生成。
长篇深度研究需在长时间跨度内进行多维度调查以获得全面报告。现有智能体虽在子任务层面管理上下文以缓解线性上下文堆积和信息丢失问题，但仍受限于单一上下文窗口与串行执行范式，导致相互干扰和阻塞行为，制约可扩展性与适应性。为此，本文提出Self-Manager，一种并行智能体循环机制，支持异步与并发执行。主进程可创建多个子线程，每个拥有独立上下文，并通过线程控制块迭代管理，实现更专注、灵活的并行智能体执行。我们在DeepResearch Bench上进行评估，结果表明Self-Manager在所有指标上持续优于现有单智能体循环基线。此外，我们开展广泛分析实验，验证了设计选择的必要性，以及其在上下文容量、效率与泛化能力方面的优势。
原文摘要 · Abstract (English)
Long-form deep research requires multi-faceted investigations over extended horizons to get a comprehensive report. When handling such complex tasks, existing agents manage context at the subtask level to overcome linear context accumulation and information loss. However, they still adhere to a single context window and sequential execution paradigm, which results in mutual interference and blocking behavior, restricting scalability and adaptability. To address this issue, this paper introduces Self-Manager, a parallel agent loop that enables asynchronous and concurrent execution. The main thread can create multiple subthreads, each with its own isolated context, and manage them iteratively through Thread Control Blocks, allowing for more focused and flexible parallel agent execution. To assess its effectiveness, we benchmark Self-Manager on DeepResearch Bench, where it consistently outperforms existing single-agent loop baselines across all metrics. Furthermore, we conduct extensive analytical experiments to demonstrate the necessity of Self-Manager's design choices, as well as its advantages in contextual capacity, efficiency, and generalization.
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。