跳到正文
Environmental Science & Technology· Zhong·· 6 天前AI 评分56

TP-Agent 用可审计 LLM 智能体预测氧化水处理中的污染物转化产物

TP-Agent: An Auditable LLM Agent for Predicting Pollutant Transformation Products in Oxidative Water Treatment

AI 导读

一项发表于 Environmental Science & Technology 的研究提出 TP-Agent,结合大语言模型、仅用训练集的类似物检索和可执行的原子/键编辑,对污染物转化产物候选排序。

AI 深度导读基于原文整理的分节解读
背景
有机微污染物在氧化水处理中的转化产物预测,对刻画其化学归趋、以及为高分辨质谱分析筛选候选结构有直接用途。但标注数据有限、反应路径多样,使这一任务一直不好做。
做法
TP-Agent 把大语言模型、仅用于训练的类似物检索和可执行的原子/键编辑组合起来,对转化产物候选排序,并给出可检查的结构记录。评测在 231 个标准化母体不重叠反应上进行,同时与裸大模型、独立的检索增强生成(RAG)和 TP-Transformer 比较。
结论
TP-Agent 取得 78.8% 的严格 Top-5 准确率,裸大模型为 65.8%,独立 RAG 为 76.2%,TP-Transformer 在三个训练种子下为 56.3 ± 1.5%。母体聚类自助分析支持其相对裸大模型的提升,但与 RAG 的 2.6 个百分点差异不具统计显著性。准确率提升主要来自检索,图执行补充的是与候选关联的结构记录;1095 个候选中 92.7% 具备精确编辑回放或确定性投影记录,该指标衡量的是结构可追溯性而非机理正确性。
意义
该工具把候选排序与可追溯的结构操作、可检查的化学假设放在一起,供高分辨质谱后续验证使用。代价是并行延迟和 API 等效成本分别约为 RAG 的 3.5 倍和 7.4 倍。

原文摘要

出版方登记 · Crossref

Predicting the transformation products (TPs) of organic micropollutants is important for characterizing their chemical fate during oxidative water treatment and prioritizing candidate structures for high-resolution mass spectrometry (HRMS) analysis. Limited labeled data and diverse reaction pathways make this task challenging. TP-Agent combines a large language model (LLM), training-only analog retrieval, and executable atom/bond edits to rank TP candidates with inspectable structural records. On 231 standardized-parent-disjoint reactions, TP-Agent achieved 78.8% strict Top-5 accuracy, compared with 65.8% for the bare LLM, 76.2% for standalone retrieval-augmented generation (RAG), and 56.3 ± 1.5% for TP-Transformer across three training seeds. Parent-clustered bootstrap analysis supported the gain over the bare LLM; the 2.6-percentage-point difference from RAG was not statistically significant. Retrieval supplied most of the accuracy gain, while graph execution added candidate-linked structural records. Among 1095 candidates, 92.7% had exact edit-replay or deterministic-projection records, measuring structural linkage rather than mechanistic validity. Where available, candidate-linked LLM rationales provide chemical hypotheses for inspection. Estimated parallel latency and API-equivalent cost were 3.5 and 7.4 times those of RAG, respectively. TP-Agent thus combines TP candidate ranking with traceable structural operations and inspectable chemical hypotheses for HRMS follow-up.

页面未能读取全文,以上为出版方登记的摘要;方法与图表见原文

本页是 AI 精读,不转载论文原文;完整论文(含方法、图表与参考文献)见原文

来源:Environmental Science & Technology · doi.org