BatchDAG: LLM-Planned Execution Graphs for Scalable Ad-Hoc Analysis Over Enterprise Data

AI 中文解读

BatchDAG让AI能一次性处理海量企业数据，速度比手工流程快几十倍，成本最低只有两分钱。以往的大语言模型面对上万条记录时，就像一个人硬背整本电话簿，要么信息超载，要么查得又慢又费钱。BatchDAG的做法很巧妙：它让AI先生成一个清晰的任务分解图，把SQL查询、语义搜索、内部分析等操作按依赖关系排好，然后用一个确定性引擎像装配流水线一样并行推进。最厉害的是“按实体分批”的优化——比如分析一万次客户对话，它会先把同一客户的对话打包，再统一分析，这样能将AI调用次数减少最多47倍。实验显示，BatchDAG在分析会议记录等任务上的质量与专家手写流程相当，但证据可追溯性更好，而且它的结构化JSON中间结果比自由文本减少27%的“胡说八道”。在实际部署中，Brevian.ai用它处理5万条会议记录的查询，不到60秒就能出结果，每次查询成本仅2到24美分。这意味着企业再也不需要为每个数据分析场景定制开发复杂流程，只要用自然语言描述任务，系统就会自动生成最优执行策略，堪称数据分析的“万能遥控器”——未来，即便没有技术背景的业务人员，也能像发条微信一样轻松搞定大规模跨实体分析。

arXiv:2607.18241v1 Announce Type: new Abstract: Large language models (LLMs) excel at analyzing individual documents but break down on exhaustive, cross-entity analytical questions over enterprise-scale datasets due to context overflow, loss of per-entity attribution, and linear latency from sequential tool calls. We present BatchDAG, a system in which an LLM generates a typed directed acyclic graph (DAG) of operations -- SQL queries, semantic searches, in-memory transforms, parallel fan-outs, and single-shot analyses -- which a deterministic engine evaluates with topological-wave parallelism and structured JSON data flow. A key optimization, entity-aware batching, groups rows by logical entity before fan-out, reducing LLM calls by up to 47x. BatchDAG is not primarily an accuracy improvement over hand-optimized pipelines; rather, it is a general-purpose orchestration layer that replaces multiple hand-engineered workflows with a single system that generates the appropriate execution strategy from natural language. In controlled experiments on 12 transcript-heavy queries, BatchDAG (3.74/5) achieves quality comparable to an expert-designed pipeline (3.25/5) and significantly outperforms a ReAct agent (3.09/5, p<0.01), with superior provenance (77% transcript evidence rate vs. 46-60% for baselines). A controlled ablation shows structured JSON intermediates reduce hallucinations by 27% versus prose summaries (paired t-test, p=0.107, n=12). The planner achieves 98.8% valid-DAG rate across 300 planning calls. In production at Brevian.ai, BatchDAG processes queries over 50,000+ meetings in under 60 seconds, with measured per-query costs of $0.02-$0.24 at published GPT-5.1 pricing.