从叙述到可审计预测：面向智能体预测的结构化脚手架
From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting
查看机构详情
- The Pennsylvania State University（宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对智能体预测缺乏结构化与可审计性的问题，提出AuditForecast脚手架，通过基线锚定、模型引导检索和几率空间更新实现结构化概率预测，提升准确性与校准度，并生成可审计报告。
中文摘要 AI 辅助
大语言模型智能体越来越多地被用于实时预测，即检索最新信息并为未解决的未来事件生成估计值。然而，当前的智能体预测往往依赖于隐式的叙述性聚合：智能体收集证据，以散文形式讨论这些证据，并常常在缺乏从证据到预测的明确更新路径的情况下分配一个概率。这限制了预测的准确性和可审计性。我们提出了AuditForecast，一种用于结构化概率预测的智能体脚手架。AuditForecast首先用合适的定量基线模型锚定预测，利用模型引导的数据检索得出基础概率，然后通过几率空间中的机械聚合，在模型范围之外应用情境因素更新。这将预测从基于散文的判断转变为具有明确中间对象的结构化过程。在多个实时预测基准上，AuditForecast相对于强大的智能体基线提高了预测准确性和校准度，在若干设置中超越了市场隐含的参考值，并且优于成本高得多的深度研究智能体，同时在成本-准确性权衡中保持帕累托优势。除了性能提升外，AuditForecast还生成一份可审计的预测报告，使预测构建过程明确化，并支持系统的后验分析。
英文摘要
LLM agents are increasingly used for live forecasting, where they retrieve up-to-date information and produce estimates for unresolved future events. However, current agentic forecasting often relies on implicit narrative aggregation: agents collect evidence, discuss it in prose, and often assign a probability without an explicit update path from evidence to forecast. This limits both forecasting accuracy and auditability. We propose AuditForecast, an agentic scaffold for structured probabilistic forecasting. AuditForecast first anchors the forecast with a suitable quantitative baseline model, uses model-guided data retrieval to derive a base probability, and then applies situational factor updates outside the model's scope through mechanical aggregation in odds space. This turns forecasting from a prose-based judgment into a structured process with explicit intermediate objects. Across multiple live forecasting benchmarks, AuditForecast improves forecasting accuracy and calibration relative to strong agentic baselines, surpasses market-implied references in several settings, and outperforms substantially more expensive deep-research agents while remaining Pareto-dominant in the cost--accuracy tradeoff. Beyond performance gains, AuditForecast produces an auditable forecasting report that makes forecast construction explicit and supports systematic post hoc analysis.
