发表机构
Indian Institute of Technology Madras（马德拉斯印度理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
BoardroomAI通过四个组件实现依赖感知的人类可引导多Agent审议，实验显示其传播效率高、修复效果好，为相关研究提出了决策充分上下文闭合的需求。
AI 中文摘要
组织决策是在证据、约束和人类优先级不断演变的过程中共同制定的。在传统的基于转录的多Agent系统中，人类通常仅提供初始问题，Agent进行内部审议，系统返回最终响应。BoardroomAI则将人类视为持续参与的参与者，可通过质疑假设、修改约束、调整优先级、引入证据或引导决策过程进行干预。我们通过四个组件实现这种人类-Agent共存：（i）类型化决策图，用于表示证据、假设、约束、主张、反对意见、替代方案、风险、决策、语义依赖和专家职责；（ii）干预编译器，将已确认的人类操作转换为显式图更新；（iii）依赖感知传播，识别受影响的子图，保留未受影响的构件，并选择性重新激活相关专家；（iv）评估框架，测量干预影响、修复覆盖率、保留情况、重新计算情况和决策有效性。在600个生成的决策DAG干预中，传播仅检查14.59%的节点，却能匹配详尽的影响计算结果。在12个案例的探索性试点中，选择性修复重新计算了62.11%的规范节点，保留了所有未受影响的标准节点，并在6个案例中生成了有效的更新决策，在剩余6个案例中弃权（不执行）。这些弃权（不执行）表明，正确的干预路由可能仍无法提供足够的综合上下文，这为人类引导的多Agent审议提出了“决策充分上下文闭合”的需求。所有结果均为合成的原型级结果。
英文摘要
Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-agent systems, humans typically provide an initial problem, agents deliberate internally, and the system returns a final response. BoardroomAI instead treats the human as a persistent participant who can intervene by challenging assumptions, modifying constraints, changing priorities, introducing evidence, or redirecting the decision process. We operationalize this human--agent coexistence through four components: (i) a typed decision graph representing evidence, assumptions, constraints, claims, objections, alternatives, risks, decisions, semantic dependencies, and specialist responsibility; (ii) an intervention compiler that converts confirmed human actions into explicit graph updates; (iii) dependency-aware propagation that identifies affected subgraphs, preserves unaffected artifacts, and selectively reactivates relevant specialists; and (iv) an evaluation framework measuring intervention impact, repair coverage, preservation, recomputation, and decision validity. Across 600 generated decision-DAG interventions, propagation matched exhaustive impact computation while inspecting only 14.59% of nodes. In a 12-case exploratory pilot, selective repair recomputed 62.11% of canonical nodes, preserved all gold-unaffected nodes, and produced valid updated decisions in six cases while abstaining in the remaining six. These abstentions show that correct intervention routing may still provide insufficient context for synthesis, motivating a \emph{decision-sufficient context closure} for human-steered multi-agent deliberation. All results are synthetic and prototype-level.
Comments14 pages, 2 figures
