Research

Paper

AI LLM March 05, 2026

SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms

Authors

Longkun Xu, Xiaochun Zhang, Qiantu Tuo, Rui Li

Abstract

Accurate time series forecasting underpins decision-making across domains, yet conventional ML development suffers from data scarcity in new deployments, poor adaptability under distribution shift, and diminishing returns from manual iteration. We propose Self-Evolving Agent for Time Series Algorithms (SEA-TS), a framework that autonomously generates, validates, and optimizes forecasting code via an iterative self-evolution loop. Our framework introduces three key innovations: (1) Metric-Advantage Monte Carlo Tree Search (MA-MCTS), which replaces fixed rewards with a normalized advantage score for discriminative search guidance; (2) Code Review with running prompt refinement, where each executed solution undergoes automated review followed by prompt updates that encode corrective patterns, preventing recurrence of similar errors; and (3) Global Steerable Reasoning, which compares each node against global best and worst solutions, enabling cross-trajectory knowledge transfer. We adopt a MAP-Elites archive for architectural diversity. On the public Solar-Energy benchmark, SEA-TS generated code achieves a 40% MAE reduction relative to TimeMixer, surpassing state-of-the-art methods. On proprietary datasets, SEA-TS generated code reduces WAPE by 8.6% on solar PV forecasting and 7.7% on residential load forecasting compared to human-engineered baselines, and achieves 26.17% MAPE on load forecasting versus 29.34% by TimeMixer. Notably, the evolved models discover novel architectural patterns--including physics-informed monotonic decay heads encoding solar irradiance constraints, per-station learned diurnal cycle profiles, and learnable hourly bias correction--demonstrating that autonomous ML engineering can generate genuinely novel algorithmic ideas beyond manual design.

Metadata

arXiv ID: 2603.04873
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-05
Fetched: 2026-03-06 14:20

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.04873v1</id>\n    <title>SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms</title>\n    <updated>2026-03-05T07:02:17Z</updated>\n    <link href='https://arxiv.org/abs/2603.04873v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.04873v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Accurate time series forecasting underpins decision-making across domains, yet conventional ML development suffers from data scarcity in new deployments, poor adaptability under distribution shift, and diminishing returns from manual iteration. We propose Self-Evolving Agent for Time Series Algorithms (SEA-TS), a framework that autonomously generates, validates, and optimizes forecasting code via an iterative self-evolution loop. Our framework introduces three key innovations: (1) Metric-Advantage Monte Carlo Tree Search (MA-MCTS), which replaces fixed rewards with a normalized advantage score for discriminative search guidance; (2) Code Review with running prompt refinement, where each executed solution undergoes automated review followed by prompt updates that encode corrective patterns, preventing recurrence of similar errors; and (3) Global Steerable Reasoning, which compares each node against global best and worst solutions, enabling cross-trajectory knowledge transfer. We adopt a MAP-Elites archive for architectural diversity. On the public Solar-Energy benchmark, SEA-TS generated code achieves a 40% MAE reduction relative to TimeMixer, surpassing state-of-the-art methods. On proprietary datasets, SEA-TS generated code reduces WAPE by 8.6% on solar PV forecasting and 7.7% on residential load forecasting compared to human-engineered baselines, and achieves 26.17% MAPE on load forecasting versus 29.34% by TimeMixer. Notably, the evolved models discover novel architectural patterns--including physics-informed monotonic decay heads encoding solar irradiance constraints, per-station learned diurnal cycle profiles, and learnable hourly bias correction--demonstrating that autonomous ML engineering can generate genuinely novel algorithmic ideas beyond manual design.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-05T07:02:17Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Longkun Xu</name>\n    </author>\n    <author>\n      <name>Xiaochun Zhang</name>\n    </author>\n    <author>\n      <name>Qiantu Tuo</name>\n    </author>\n    <author>\n      <name>Rui Li</name>\n    </author>\n  </entry>"
}