TimeEvo is proposed, which clusters an agent's diagnosed failures into capability gaps, plans a measurement for each, synthesizes evidence-only tools that fill them, and admits the candidate library only through a paired admission gate.
Abstract
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, while tools are supplied in advance and judged by a single average. To address this, we propose TimeEvo, which clusters an agent's diagnosed failures into capability gaps, plans a measurement for each, synthesizes evidence-only tools that fill them, and admits the candidate library only through a paired admission gate. Experiments on ten time series QA tasks and three backbones show that TimeEvo, starting from an empty library, improves accuracy on every task and every backbone, and that a library grown on a cheap model still gains when it is installed into stronger ones. Code is available at https://github.com/Muyiiiii/TimeEvo.
This work presents a self-evolving agent framework that reduces the consistency gap by identifying unstable, low-consistency steps in agent trajectories and converting them into episodic memory the agent can draw on in future runs.
Evelyn Duesterwald, Benjamin Elder, Lilian Ngweta et al.· 0 citations
TimeSage-EV is introduced, a live benchmark for agentic time series analysis in evolving environments that evaluates state identification, data summarization, and outlook reasoning, and is released as a research resource with monthly updates, code, a leaderboard, and failure-mode analyses.
Qingren Yao, Ya-Xuan Kong, Yuqi Nie et al.· 0 citations
This work defines real-time as five measurable properties, each with an equation and a worked example: continuous task arrival, live concurrent execution, online rating updates, freshness with contamination resistance, and bounded feedback latency from a failed run to a reusable training environment.
DolphinBench is presented, a benchmark that evaluates memory directly through an agent's task completion and requires all evaluations to report total cost and latency alongside accuracy, which enables us to evaluate agent memory systems holistically.
Agent evaluations should be evaluated as configurable systems themselves, and that some desired behaviors are more effectively implemented in the system than requested through prompting, according to a new benchmark of four scientific tasks.
Luis Wiedmann, Leander Girrbach, Cordelia Schmid et al.· 0 citations
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 d...
Lei Jiang, Yehua Wei, Xinyu Xi et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.