- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a test-time method that improves forecasting accuracy by repeating a selected window of encoder blocks in a frozen time-series foundation model (Chronos-2). The extra cost of each repetition scheme is known exactly in advance. An LLM searches for a scheme per task using errors measured on historical windows, and the chosen scheme is deployed only after passing a held-out verification check. Across 56 tasks, it reduces test MSE relative to the base Chronos-2 model, at controllable computation cost relative to base.
Critical strengths
- The paper treats the internal execution path of a frozen time-series foundation model as test-time compute allocation. It has a certain degree of novelty and parallels layer-looping work in language models.
- The extra cost of repeating encoder blocks is known exactly before running, which makes budget-aware deployment capable.
Critical weaknesses
- The paper provides some initial analysis, but it is mostly correlational, lacks intervention experiments, and does not explain why different tasks benefit from repeating blocks at different positions, or how different encoder block position changes the forecast.
- The method relies on Chronos-2's specific context and future token structure and is evaluated only on Chronos-2, so it is unclear whether it transfers to other time-series foundation models.
- Each task uses at most 18 candidate programs, while Chronos-2 has only 12 encoder blocks and the program space is low-dimensional. Maybe rule-based methods such as random or grid search might perform comparably? But the paper does not compare against them, so the necessity of the LLM reasoner is not fully demonstrated.
Questions for authors
- Did you observe typical forecast changes when repeating encoder blocks at different positions (e.g., corrections to trend, seasonality, or volatility)? Is there a systematic relationship between the repetition position and series characteristics such as autocorrelation, volatility shift, or cross-channel correlation?
- How would this design transfer to other models that not follow Chronos-2's joint context and future token structure?
- The method is conceptually close to loop transformer architecture. Beyond being training-free, what is the essential difference between your work and loop transformer?
6 comments
W2: Comparisons with conventional search methods.
This concern (is LLM-guided search needed?) was also raised by Reviewers VmaH and w4Zx. To address this concern, we conducted the requested comparisons against conventional search methods. Our results show that LLM-guided recipe generation achieves much larger forecasting improvements under the same candidate-evaluation budget.
Our Sol-based reasoner finds more effective recipes than uniform random search and the three adaptive search methods we evaluated under the same 18-candidate budget. Although Chronos-2 has only 12 encoder blocks, the search involves much more than selecting a block position. These comparisons directly check whether conventional search can recover the gains of LLM-guided recipe generation within the paper’s search budget.
All methods search the same legal recipe space. Chronos-2’s 12 blocks define 78 contiguous block ranges, with additional choices of repetition count, solver, and update strength. We evaluate 60 tasks spanning 15 datasets and four horizons per dataset, using the same candidate-evaluation budget, final validation selector, and test protocol for every method.
The baselines include the suggested uniform random search, which samples recipe parameters without feedback. The Tree-structured Parzen Estimator (TPE) [1] uses previous evaluations to propose promising configurations. Differential evolution (DE) [2] mutates and recombines parameter vectors. Monte Carlo tree search (MCTS) [3] explores a tree of recipe choices using Upper Confidence Bounds applied to Trees (UCT). The adaptive searches receive their own training MSE feedback. The LLM-guided workflow additionally uses model knowledge and task information to construct and revise proposals.
The differences are quite meaningful. Random search does not reproduce the observed gains. Its average MSE is essentially unchanged (+0.001%), while MAE increases by 1.41%. Sol reduces average MSE by 4.15% and MAE by 0.94%, improving MSE on 53/60 tasks. MCTS, the strongest of the four conventional searches by average MSE, achieves a 1.97% reduction and improves 33/60 tasks. All four conventional searches worsen average MAE. With final selection held fixed, these results support the role of LLM-guided candidate generation under the limited evaluation budget.
The advantage also appears with a smaller local reasoner. Qwen3-4B-Thinking-2507 reduces average MSE by 3.00% and MAE by 0.71%, exceeding the tested searches on both aggregate metrics.
[1] Bergstra et al. Algorithms for Hyper-Parameter Optimization. NeurIPS, 2011.
[2] Storn and Price. Differential Evolution: A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces. Journal of Global Optimization, 1997.
[3] Kocsis and Szepesvári. Bandit Based Monte-Carlo Planning. ECML, 2006.
Table 2: Local and API reasoners versus conventional search for Chronos-2 looping recipes. All methods are evaluated on 60 tasks. B/T/W = Better/Tie/Worse. API models use low reasoning effort.
| Type | Model | MSE Avg Δ% ↓ | MSE B/T/W | MAE Avg Δ% ↓ | MAE B/T/W |
|---|---|---|---|---|---|
| Local | Qwen4B | -3.00% | 48/7/5 | -0.71% | 36/7/17 |
| Local | DeepSeek8B | -1.42% | 50/7/3 | +0.15% | 37/7/16 |
| API | Luna-low | -3.36% | 46/3/11 | -0.72% | 40/3/17 |
| API | Sol-low | -4.15% | 53/4/3 | -0.94% | 48/4/8 |
| API | Terra-low | -3.78% | 49/7/4 | -0.80% | 40/7/13 |
| Search | Uniform | +0.001% | 17/29/14 | +1.41% | 5/29/26 |
| Search | TPE | -1.14% | 28/23/9 | +0.69% | 16/23/21 |
| Search | DE | -0.43% | 25/23/12 | +1.14% | 15/23/22 |
| Search | MCTS | -1.97% | 33/18/9 | +0.54% | 19/18/23 |
Q1: Analysis of looping positions.
This is a very interesting question. We have done additional analyses to address what looping changes in the forecasts, why position of repetition matters, and how these effects relate to time-series characteristics. We go beyond the correlational analysis by decomposing the forecast corrections and directly measuring how their individual components affect prediction error.
First, we examine which changes in the forecasts are responsible for the improvements. For the 56 selected recipes on 16 test origins per task, we orthogonally decompose the forecast correction (Loop minus Base) into interpretable components and evaluate each component by adding it separately to the Base forecast. Level (constant shift) and trend (slope change) account for 61.5% and 14.1% of the net macro MSE gain, respectively, totaling 75.6%. A harmonic at a frequency estimated from training contributes 3.0%. Remaining changes contribute 21.4% and may include curvature, local adjustments and other frequencies. So**, the largest improvements come from correcting the forecast's level and trend.**
Second, we check how these forecast corrections differ depending on where blocks are repeated. Looping adjusts both periodic amplitude and peak timing, with amplitude changes occurring in both directions. Across 41 matched pairs of beneficial recipes from 1,000 reasoner proposals, early repetition increases the fitted periodic amplitude in 31.1% of channel forecasts and decreases it in 64.5%. At late positions, the corresponding rates are 12.9% and 82.9%, with approximately 4% unchanged at either position. These rates are averaged equally across datasets. Later repetition also produces larger shifts in the timing of fitted periodic peaks and troughs relative to Base, with mean absolute phase changes of 0.14 versus 0.04 radians. So, these results show that repetition at different block positions produces different forecast corrections. Basically late repetition more frequently attenuates periodic amplitude and produces larger phase adjustments.
Third, we check whether the relative benefit of early and late repetition is related to properties of the input series. Later repetition tends to offer a larger advantage when channels are more strongly related. Across eight datasets with 512-step histories, historical absolute cross-channel correlation is associated with a larger late-over-early level calibration benefit (Spearman rank correlation is 0.67). Omitting each dataset in turn preserves the positive association, so its direction does not depend on one dataset.
We believe these experiments give a clean and accurate account of how our recursive inference improves forecasting.
We sincerely thank Reviewer pAjG for the thoughtful feedback and constructive suggestions, which have helped us further improve our work. We address each point below.
The concern about generalization beyond Chronos-2 is very reasonable and was also raised by Reviewers VmaH and w4Zx. To address this shared concern, we conducted additional experiments on a second time-series foundation model, Timestral-209M. Here, we also address the reviewer's more specific question: whether RI depends on Chronos-2's particular context and future-token structure.
RI can transfer through repetition of native Transformer blocks without requiring Chronos-2’s joint context and future-token structure. Selectively updating future-token representations is an execution option available for Chronos-2, but not a requirement of our RI idea. For a model without that partition, the model adapter can instead expose recipes that repeat complete blocks over their full hidden state, preserving the model’s native attention and inference semantics. The reasoner then proposes recipes using the execution choices supported by that architecture.
We implemented and evaluated this approach in Timestral-209M with Claude Haiku 5.5. Timestral encodes context causally and uses separate prediction tokens that attend to the context, while context tokens do not attend back to them [1]. Our implementation repeats complete native blocks across both streams, retaining their original attention masks, positions, and feed-forward computations. The reasoner gets Timestral’s block structure and task information, such as the forecasting horizon, and revises its proposals using forecasting feedback from training data. All forecaster weights remain frozen.
The transferred workflow finds useful recipes under these different token interactions. Across the reported 12 datasets covering 48 tasks, RI with Haiku achieves mean dataset-level reductions of 5.97% in MSE and 1.08% in MAE, after averaging four horizons within each dataset. MSE improves on 11 of 12 datasets, and the mean reduction remains 2.18% even when excluding Covid-19, which has a particularly large gain. The results support transferring the proposal-and-feedback workflow through the target model's native computation (with its own token structure preserved).
Our Timestral implementation also produces average gains with Sonnet in the eight-task comparison. Under the same workflow and candidate budget, average MSE/MAE reductions are 13.77%/2.53% with Haiku and 14.52%/3.00% with Sonnet, providing supplementary evidence across reasoner choices. So, our main point is that RI does not need a particular token-update mechanism. It assigns/allocates compute using the execution choices supported by the target forecaster. Our Timestral experiments show that this approach remains effective with a different attention structure and native full-block repetition.
Table 1. Generalization to Timestral-209M with Claude Haiku 5.5. Results cover 12 datasets and 48 forecasting tasks. MSE and MAE are averaged over four horizons within each dataset. The Average row reports the mean dataset-level percentage change. Δ denotes percentage change relative to Base. Negative values indicate lower forecasting error.