发表机构
Amazon（亚马逊）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究用大语言模型代理从长篇时间结构化文本中决策的问题，针对标准RAG丢弃时间结构缺陷，引入闭环代理框架TLM，其关键技术是LGCM，在医学问答、收益电话会议惊喜预测和隔夜股票缺口预测任务中表现出色。
AI 中文摘要
我们研究了使用大语言模型（LLM）代理从长篇、时间结构化文本中进行决策的问题。标准检索增强生成（RAG）管道将按时间顺序的上下文片段化为孤立的片段，丢弃了对正确下游决策通常至关重要的时间结构。我们引入了TLM（轨迹语言模型），这是一个闭环代理框架，它使用SHAP引导的反馈迭代地完善证据集。关键技术贡献是检索到的块嵌入上的潜在增长曲线模型（LGCM），它提供了一种可解释的机制来检测轨迹趋势、转折点和信息差距。我们表明，在评分器校准假设（在实践中大致成立）下，迭代细化过程在分配给正确标签的概率上单调不减。通过实证，TLM在三个时间基础的决策任务上进行了评估：医学问答、收益电话会议惊喜预测和隔夜股票缺口预测。在医学任务上，TLM显著优于零样本LLM基线和标准检索增强方法，并在两个金融任务上产生了一致的、具有经济意义的收益
英文摘要
We study the problem of decision-making from long-form, temporally structured text using large language model (LLM) agents. Standard retrievalaugmented generation (RAG) pipelines fragment chronological context into isolated snippets, discarding the temporal structure that is often critical for correct downstream decisions. We introduce TLM (Trajectory Language Model), a closed-loop agentic framework that iteratively refines the evidence set using SHAP-guided feedback. The key technical contribution is the latent growth curve model (LGCM) over retrieved chunk embeddings, which provides an interpretable mechanism for detecting trajectory trends, turning points, and information gaps. We show that, under a scorer-calibration assumption (which holds approximately in practice), the iterative refinement procedure is monotonically non-decreasing in the probability assigned to the correct label. Empirically, TLM is evaluated on three temporally grounded decision tasks: medical question answering, earnings call surprise prediction, and overnight stock gap prediction. TLM substantially outperforms both zero-shot LLM baselines and standard retrieval-augmented approaches on the medical task, and yields consistent, economically meaningful gains on the two financial tasks.
