LLM Digest

Story

arxiv_cs_ai · Aug 18, 2026 · paper

Source brief

EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection

arxiv.orgAug 18, 2026
original source linked

In brief

Financial time series exhibit non-stationary and heterogeneous statistical properties, making change-point detection challenging because no single unsupervised algorithm performs consistently across assets and market...

Feed lens

agenteval

Read the original at arxiv.org →Open in live feed Read that day’s brief

EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection

Earlier in this thread 4 items

Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection

TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems

SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis

Lessons from Building Evals for Financial AI Agents