- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper provide an oracle study whether varying where and when the model writes can outperform the best constant write action for in-place test-time training. The experiment results show that some dynamic trajectories can outperform the best constant write action. Besides, the paper provides some observations in the update of test-time training, which may provide insights for the method design.
Critical strengths
- Studying dynamic strategies for deciding which parameters to update during TTT is an interesting research direction.
Critical weaknesses
- The action space is limited. The paper only considers updating layers 0, 6, 12, 18, and 24, either updating a single one of these layers, updating all of them, or updating none of them. The authors do not explore updating arbitrary combinations of these layers. I think that, for a given chunk, the set of parameters that should be updated is unlikely to be restricted to the action space considered in the paper. Moreover, I do not fully understand why there should be an optimal single layer to update for a particular chunk, or what the underlying relationship is between the content of a chunk and the layer that is best to update.
- The main contribution consists of exploratory experiments showing that dynamic scheduling can be beneficial, but the paper does not propose any scheduling approach that can operate without access to an oracle, even a simple one. This makes the overall contribution feel somewhat limited to me.
Questions for authors
see weaknesses
3 comments
Response2
W1(b). How does chunk content relate to the layer to update?
Chunk content affects later computation through the update it produces. The selected layer determines where that update enters the model. Each chunk is first read using the weight state accumulated so far, then writes to the selected layers for use by later chunks. We therefore compare complete trajectories to examine how a chunk's write location and the preceding state affect subsequent outputs.
Two functional studies motivate this comparison. Meng et al. (2022) use causal tracing and ROME to identify a role for middle-layer MLPs in factual associations [2]. Todd et al. (2024) locate task representations in attention heads through function-vector interventions and compare their effects across depths [3]. We build on these findings by comparing write sites across depth with the model and update rule held fixed.
Trajectory comparisons measure score differences due to location and timing. Reversal changes the write schedule, while resetting and deletion remove accumulated writes. These experiments directly test how write schedules and retained state affect subsequent outputs. We will add this functional motivation after the action definitions in Section 2.1. At the start of each intervention in Sections 3, we will specify the write schedule or accumulated state being changed and the comparison conditions held fixed.
W2. Can a practical scheduling method work without an oracle?
We use the frozen Qwen3-1.7B checkpoint with the same chunking. The five writable sites are {0, 6, 12, 18, 24}. Their every-sixth-layer layout follows Feng et al. (2026), In-Place Test-Time Training [1, Section 9.3]. We introduce range and dose checks that control writes using training-document calibration and the current input's update state in a single pass. The rule has been evaluated on 6,500 fresh inputs.
- Range check, first chunk. For each of layers 0, 6 and 12, compare the norm of its first proposed update with that layer's 99th-percentile threshold on training documents. With , the rule is
Reference
[1] Feng, G., Luo, S., Hua, K., Zhang, G., He, D., Huang, W., & Cai, T. (2026). In-Place Test-Time Training. arXiv:2604.06169v1. Section 9.3, “Details of Model Configuration”, PDF page 20. Section link: https://arxiv.org/html/2604.06169v1#S9.SS3.
[2] Meng, K., Bau, D., Andonian, A., & Belinkov, Y. (2022). Locating and Editing Factual Associations in GPT. NeurIPS 2022. arXiv:2202.05262. Sections 2.2 and 3.1. Paper: https://arxiv.org/abs/2202.05262.
[3] Todd, E., Li, M. L., Sen Sharma, A., Mueller, A., Wallace, B. C., & Bau, D. (2024). Function Vectors in Large Language Models. ICLR 2024. arXiv:2310.15213. Sections 2.3 and 3.1. Paper: https://arxiv.org/abs/2310.15213.
Response1
Response to Reviewer ixGy
Thank you for your review, suggestions, and requests for further clarification. Below, we provide a constant-action experiment over all 32 layer combinations, the functional motivation linking chunk content to write location, and an answer-free write rule evaluated on 6,500 fresh inputs to address each of the concerns raised. We hope these revisions and clarifications strengthen your confidence in our work and support a positive evaluation.
W1(a). Why these seven actions, and what about other layer combinations?
We have evaluated all 32 constant subsets of the five writable layers on 300 examples. Each subset is held constant throughout the input, giving 9,600 full replays. CO selects the highest-scoring constant action for each example.
The full set raises CO by 2.76 percentage points (95% CI [1.49, 4.33]). A combination outside the original seven scores higher on 16 of the 300 examples. In comparison, enumerating seven constant actions on the same 300 examples requires 2,100 full replays, compared with 9,600 for 32 actions: 7,500 additional replays, or about 4.57 times as many candidate evaluations. The expanded set thus yields a modest score gain at a substantially higher evaluation cost.
The writable sites follow Feng et al. (2026), In-Place Test-Time Training [1, Section 9.3], which places MLP write modules every sixth layer. Our checkpoint uses this layout, with five writable sites at {0, 6, 12, 18, 24}. We construct OFF, five single-layer actions and ALL to compare stopping new writes, writing to one layer and writing to all five. OFF retains existing state, the single-layer actions vary write location individually, and ALL tests joint writing.
Functional studies across depth provide further motivation: middle-layer MLPs participate in factual associations [2], and interventions on task representations have depth-dependent effects [3]. We therefore hold the model and update rule fixed, compare writes at five sites spanning depth, and use state interventions to study their effects on later computation. The seven actions place stopping, single-layer writing and joint writing in the same experiment, helping distinguish the contributions of location, timing and accumulated state.
Searching all 32 subsets shifts the focus to finding the highest-scoring configuration. When several layers change together, a combination's score pools layer contributions and their interactions. Explaining those contributions then requires breaking the combination apart and testing its components. We study how write location, timing and accumulated state affect the output, and retain single-layer actions as direct controls while using ALL to test joint writing.
Dynamic expansion additionally selects a subset at every chunk. With K actions and T complete chunks,
Nfixed(K)=K,Ndynamic(K,T)=∏t=1TK=KT.
Five writable layers give 25=32 subsets, expanding the full dynamic space from 7T to 32T. For T=2, the candidate count rises from 49 to 1,024. Bounded search evaluates part of this space, with 32 action alternatives at each search position instead of seven. Each added-candidate evaluation currently involves full replay and generation, and running this search online would add forward computation. Given our research objective and this computational cost, we completed all 32 constant combinations in this revision and retained the seven-action design for dynamic experiments. The dynamic expansion exceeds the time and compute budget for this revision.
After the action-space definition in Section 2.1, we will add the layout source, the rationale for the seven actions and the candidate-space formula. A new “Action-space expansion” subsection in Appendix B will present the completed 32-combination table above and account for the 2,100 versus 9,600 full replays.