# TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH

arXiv: https://arxiv.org/abs/2608.16410 · HTML: https://mlsanity.com/paper/2608.16410/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 9 of 9)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [Large Language Models to Enhance Bayesian Optimization](https://mlsanity.com/paper/2402.03921/) (2024)
- [YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization](https://mlsanity.com/paper/2109.03670/) (2021)
- [Sequential Large Language Model-Based Hyper-parameter Optimization](https://mlsanity.com/paper/2410.20302/) (2024)
- [Review of automated time series forecasting pipelines](https://mlsanity.com/paper/2202.01712/) (2022)
- [AutoAI-TS: AutoAI for Time Series Forecasting](https://mlsanity.com/paper/2102.12347/) (2021)
- [Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH](https://mlsanity.com/paper/2601.12355/) (2026)

## Abstract (arXiv)

Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparameters are active. In time-series forecasting, temporal choices, chronological validation, and costly evaluations further complicate this search. Controlled comparisons of heterogeneous search methods under a shared time-series CASH (TS-CASH) evaluation protocol remain limited. Within this setting, we study TRACECASH, a task-local hybrid sequential optimizer combining grouped actor-critic candidate generation with fixed rules for model coverage, validation-guided exploitation, and exploration after stalled progress. A model actor proposes an initial forecasting model; three model-conditioned actors generate temporal, architectural, and training actions; and a modelspecific decoder constructs the configuration ultimately evaluated. We compare TRACE-CASH with six alternatives spanning random, Bayesian, evolutionary, multi-objective, and language-model-assisted search across 41 dataset-frequency task variants. TRACE-CASH has the lowest mean rank on both MASE and WQL. Descriptively, it also has the lowest window-averaged test-MASE rank in the predefined full and late windows. These results support the complete TRACECASH procedure as competitive among the evaluated methods.