SOURCE-LINKED INTELLIGENCE

TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However, we identify two failures in this setup. Human-Agent Tool Misalignment: a library of 21 expert-curated tools helps on some tasks and hurts on others, dropping anomaly accuracy under every backbone we test. Silent Harm: one round of generic self-revision changes 147 answers and breaks 56 of them, while the final score moves by less than a point. Both follow from the same gap: whether a tool helps is decided question by question at runtime, whil

Read original source ↗ Open in workspace

recordType

paper

region

Global