多智能体协作研究自动化，先思后行更高效。
DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation
- 先深度思考再调用工具，结合用户模型与上下文理解
- 三阶段协同推理提升答案可信度与信息覆盖
- 六级预算分配降低40%-60%计算成本，适合复杂研究
大语言模型智能体在工具使用、推理和代码生成方面表现优异，但在需要多源整合、对抗验证与个性化输出的复杂研究任务中仍存在局限。我们提出DOVA（Deep Orchestrated Versatile Agent）多智能体平台，引入三项核心创新：(1) 先思后行的编排机制，通过持续的用户模型与实体感知对话上下文，在调用工具前进行显式元推理；(2) 混合协作推理，采用可组合的三阶段流程，融合集成多样性、共享白板透明性与迭代优化；(3) 自适应多层级思维，基于六级令牌预算分配策略，在简单任务上降低40%-60%的推理开销，同时保持深层推理能力。我们形式化核心算法，对七种系统配置进行架构消融分析，并评估各组件对答案置信度、来源覆盖率与令牌效率的贡献。
原文摘要 · Abstract (English)
Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation, yet single-agent systems exhibit fundamental limitations when confronted with complex research tasks demanding multi-source synthesis, adversarial verification, and personalized delivery. We present DOVA (Deep Orchestrated Versatile Agent), a multi-agent platform introducing three key innovations: (1) deliberation-first orchestration, where explicit meta-reasoning precedes tool invocation, informed by a persistent user model and entity-aware conversation context; (2) hybrid collaborative reasoning, a composable three-phase pipeline unifying ensemble diversity, blackboard transparency, and iterative refinement; and (3) adaptive multi-tiered thinking, a six-level token-budget allocation scheme that reduces inference cost by 40-60% on simple tasks while preserving deep reasoning capacity. We formalize the core algorithms, present an architectural ablation study across seven system configurations, and analyze the contribution of each component to answer confidence, source coverage, and token efficiency.
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。