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

arXiv:2608.17933v1 Announce Type: new Abstract: 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 regimes. Conventional workflows consequently depend heavily on expert-driven model selection, feature design, and hyperparameter tuning, limiting their scalability and adaptability. We propose EvoTS-Agent, a validation-guided self-evolving LLM agent for autonomous financial time-series change-point detection. EvoTS-Agent first performs curated exploratory data analysis to characterize dataset properties and initialize candidate detection models. It then evolves executable experiment trajectories through three complementary operators: extit{Revision} exploits the current best solution, extit{Alternative Strategy} explores fundamentally different modeling directions when progress stagnates, and extit{Recombination} synthesizes complementary evidence from high-performing trajectories. Validation feedback guides trajectory evolution throughout the search, enabling the agent to adapt its detection pipeline to the statistical characteristics of each dataset while preserving reliable optimization. Experiments across four benchmark datasets demonstrate that EvoTS-Agent consistently outperforms existing LLM-based agents while maintaining a 100% execution success rate across all evaluated backbone LLMs.

Related

• FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
• Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
• Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents

Source: arXiv cs.AI | 2026-08-19