Skip to content

When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting

Sep 2026 · 2 citations · 40 references
Computer Science

TL;DR

TimEvolve is introduced, a frozen-backbone time series agent that converts each realized outcome into persistent joint updates of expert trust, agent path selection, and intervention strength, and demonstrates the value of learning forecasting policies from the futures encountered during deployment.

Abstract

Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning strategies, and intervention rules inherently time-varying. Consequently, a time series agent must adapt the forecasts it produces and the orchestration policy that determines which components to trust and how to coordinate them. The deployment process naturally provides supervision for this adaptation as forecast horizons elapse and realized targets reveal the effectiveness of earlier decisions. Committing all numerical expert forecasts and candidate agent paths before target observation allows each realized outcome to evaluate the entire alternative set, providing delayed feedback without additional annotation. However, existing time series agents primarily incorporate prior experience through forecast refinement, reflection, or retrieval, without systematically converting realized outcomes into persistent updates to the joint orchestration policy governing later origins. To exploit this delayed feedback systematically, we introduce TimEvolve, a frozen-backbone time series agent that converts each realized outcome into persistent joint updates of expert trust, agent path selection, and intervention strength. A temporally ordered predict, reveal, and update protocol applies this feedback to subsequent forecasts. Experiments across eight Time-MMD domains show that TimEvolve achieves the best average MSE and MAE ranks among fifteen methods and the lowest errors on both metrics in seven domains. These results demonstrate the value of learning forecasting policies from the futures encountered during deployment.

View source

Similar papers

Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning

LLM-based agents are increasingly used for time-series forecasting because they can organise contextual information, perform multi-step analysis, and guide the sequence of actions required to complete forecasting tasks. Most existing agents focus only on the current forecasting instance. However, in real-world deployme...

Jun-Yi Wang, Yi-Lin Wang, Wen Wu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution

EvoCast is introduced, a fully autonomous research-agent system for iterative forecasting architecture evolution that establishes and diagnoses a task-specific baseline, and develops task-specific architectures that outperform selected baselines, strong forecasting models, and agent baselines in three real-world foreca...

Kai-Peng Xu, Xiang Yan, Yan Wang et al. · 0 citations

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

Experiments show that EvolveTrade often improves Sharpe Ratio and Cumulative Return over fixed-policy LLM baselines, achieving the improved SR and CR in most evaluated settings, and suggest that adapting the reusable procedure governing tool use is a key direction for building more robust LLM trading agents.

Sehee Kim, Yumin Choi, Minki Kang et al. · 1 citation
#artificial intelligence Preprint Oct 2026

ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents

Interactive language-model agents increasingly solve complex tasks through long-horizon, multi-call reasoning, where errors in beliefs or actions can compound across tool interactions. Retrospective search can recover from such failures but is prone to misallocation. Delayed outcomes obscure the contribution of interme...

Xin-Yue Zeng, Shivam Shandilya, Guilherme Potje et al. · 0 citations
Preprint Sep 2026

CompEvo: Competition-Induced Evolution for Multi-Agent in News-Driven Time Series Forecasting

This work proposes CompEvo, a trainable multi-agent evolution framework that integrates strategy execution, fitness-based differentiable selection, and competition-induced strategy evolution that enables heterogeneous agents to explore diverse news evidence, converts forecasting feedback into differentiable influence w...

Yuxuan Zhang, Yang-Yang Feng, Yong Guan et al. · 0 citations
#artificial intelligence Preprint Oct 2026

JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models

Long-horizon autonomous research has shown promise in accelerating scientific progress through sustained cycles of hypothesis generation, implementation, and validation. However, this Generate-Execute-Feedback paradigm relies on reactive trial-and-error, where costly and time-consuming executions introduce severe feedb...

Meng-Di Liu, Cheng-Hao Jia, Hong Chang et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.