English(EN) TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue

新的TrackMem记忆系统增强了用于金融分析的LLM对话

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 05:00

研究人员开发了TrackMem，这是一种新颖的、每个说话者的图记忆系统，旨在提高LLM代理在长时金融对话中的性能。与难以处理不断变化信息的传统记忆系统不同，TrackMem追踪历史人物，按实体和分析视角分离观点，并保留时间顺序的行动。该系统使用FinLoCoMo进行了评估，FinLoCoMo是一个包含15个长时投资对话的新基准，TrackMem在该基准上显示出比现有记忆系统更高的准确性，尤其是在回忆修订后的数字和规则方面。 AI

影响提高了LLM代理在复杂、不断变化的对话场景中的能力，可能增强金融分析工具。

排序理由学术论文介绍了一种新的LLM记忆系统。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 41 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文介绍了一种新的LLM记忆系统。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Austin M. Y. Cheung, Harsh Vardhan Gupta, Go Nam Lui, Lok Kan Chan, Ginny Y. Wong, Simon See · 2026-11-04 05:00

TrackMem：追踪金融长对话中不断演变的信念

arXiv:2611.02001v1 Announce Type: new Abstract: Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which something was said. Financial dialogue breaks this assumpti…

本文如何被排名

报道来源 [1]

TrackMem：追踪金融长对话中不断演变的信念

相关实体

相关话题