Test-Time Training

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 46

Oct 1, 2026cs.AI

Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning

Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: RNNs suffer from vanishing gradients and the limited expressivity of vector-based hidden states, whilst Transformer-based models are limited by the quadratic scaling of attention. Recent work has proposed tackling this problem with the Test-Time Training (TTT) framework, which stores episodic memories in the parameters of a neural network through gradient descent at both train and test-time. This approach has seen success in the domain of Natural Language Processing, however, to the best of our knowledge it has not yet been applied to the domain of Reinforcement Learning (RL), nor has there been a study analysing how this memory practically functions. In this paper, we study the potential of the TTT framework for offline RL by augmenting a Decision Transformer with TTT layers, dubbed the Decision Titan. We analyse performance and properties of the model in the X-Maze environment, an extension of T-Maze designed to test sequential memory, and investigate how the memory mechanism learns by visualising gate values over time. Our key findings are that Decision Titan can learn long-term dependencies with ranges 20x longer than the context window, generalises to lengths 1.7x the training data, but crucially temporal generalisation depends on the time embeddings used, and the ability to learn long-term dependencies depends on how the relevant information is encoded.

Jude Waide, Robert Lieck

Department of Computer Science, University of Durham, Durham, United Kingdom.

Test-Time Training Long-Term Memory Transformer Architectures

Sep 30, 2026cs.LG

JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts

World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during training. We present JEPA-TTT, which adapts the latent dynamics predictor of a pretrained action-conditioned Joint-Embedding Predictive Architecture world model throughout test time. Self-supervised updates accumulate across episodes, while the visual encoder and reward head remain fixed, preserving the pretrained representation and task objective. Planning requires neither a goal image nor online environment reward. JEPA-TTT uses dense replay, which forms prediction windows at every temporal offset, retains them in a growing buffer, and samples minibatches from that buffer for predictor updates. Across eight dynamics shifts in four continuous-control environments, JEPA-TTT improves planning on every shift. After 500 test-time episodes, it reduces autoregressive latent prediction error by 83% on average and improves planning performance by 153% over the frozen JEPA world model. These results show that persistent self-supervised test-time training can adapt a pretrained latent world model under changed dynamics.

Zheyuan Zhang, Suyu Ye, Nakul Agarwal +5

Honda Research Institute USA · Johns Hopkins University

Latent World Models Test-Time Training S-Jepa Planning Self-Supervised Learning

Sep 28, 2026cs.LG

Transferable Mass Spectrum Prediction via Reference-Guided Test-time Specialization

Tandem mass spectrum prediction supports compound identification across metabolomics, natural-product discovery, and environmental analysis. However, pretrained predictors often degrade under shifts in chemical space and acquisition conditions, while retraining domain-specific models from scratch is costly. We introduce SPARC, a retrieval-guided test-time specialization framework that adapts a pretrained predictor using a spectral reference library without accessing test-query spectra. For each target query, SPARC retrieves chemically related reference spectra to recalibrate fragment intensities within the learned fragmentation space. During Transfer, SPARC combines reference-guided spectral adaptation with reliability-aware consistency, using reconstruction behavior on retrieved spectra to selectively preserve trustworthy predictions during continual specialization. Across MassSpecGym, NPLIB1 and application-specific GNPS libraries, SPARC improves spectral prediction under multiple transfer settings. These results establish retrieval-guided test-time specialization as a practical strategy for extending pretrained MS/MS predictors to specific chemical and acquisition domains, with continual test-time training providing further refinement during deployment.

Yunhua Zhong, Runting Li, Yifan Li +5

The Hong Kong University of Science and Technology (Guangzhou) · The University of Hong Kong · South China University of Technology +3

Tandem Mass Spectra Metabolic Molecular Property Prediction Spectral Test-Time Training Test Time

Sep 28, 2026cs.LG

GradLev: Token-Parallel Test-Time Training Via Costate Prediction

Test-time training (TTT) allows a model to improve its predictions at inference time by updating weights after every observed token. However, sequential gra- dient writes make parallel training difficult. We observe that, given layer inputs and activation gradients (costates), online gradient descent admits exact parallel scans for both forward evaluation and reverse backpropagation. GradLev lever- ages this duality: a causal auxiliary network predicts costates across all tokens in parallel; associative scans compute the adapted weights and forward activations and propagate gradients backward; and the resulting gradient targets supervise the predictor via a consistency loss. Exact consistency guarantees exact recovery of the sequential online learner. At deployment, the auxiliary predictor is discarded, and the model updates natively via token-by-token forward and backward passes.

Bo Liu, Qiang Liu

The University of Texas at Austin

Test-Time Training Inference-Time Next-State Prediction Causal Graph

Sep 27, 2026cs.CV

Position Aware Layer Queries for Test Time Training in Vision Language Models

Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (OOD)) when conventional fine-tuning is infeasible. Existing TTT methods for Vision-Language Models (VLMs) create supervision from several augmented views, each requiring forward (and often backward) passes through the entire VLM, incurring substantial computational cost. We observe that one forward pass with all the intermediate layer outputs already yields far more signal than the final embedding from all augmentations. We introduce Layer Query Network (LQN), a lightweight approach that can adapt a frozen VLM (teacher) in a single forward pass of the VLM via a small model (student). LQN uses Position-Aware Distillation (PAD) to mimic the teacher VLM's intermediate-layer spatial tokens by querying spatial coordinates of intermediate tokens. LQN additionally relies on Location Consistency Regularization (LCR), a self-supervision technique, replacing expensive O(H x W) image augmentation with O(1) coordinate sampling. Integrating these, LQN i) adapts and improves zero-shot CLIP ViT-B/16 by 9.8% Top-1 on OOD ImageNet, ii) outperforms the previous best GS-Bias on fine-grained classification by 3.9% Top-1, iii) achieves faster convergence than TPS for CLIP ResNet-50 (47 mins vs 55 mins), iv) generalizes adaptation to VLMs like SigLIP, EVA-CLIP, and CoCa, and lightweight students like MLP, ResNet, VGG, and v) extends to panoptic, instance, and semantic segmentation.

Rajat Modi, Priyank Pathak, Xin Liang +1

Institute of Artificial Intelligence University of Central Florida Orlando, FL 32816, USA

Frozen Contrastive Language-Image Pre-Training Visual Encoder Test-Time Training Out-Of-Distribution Detection Queries

Sep 8, 2026cs.CV

LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation

Delineating lung tumours on computed tomography (CT) takes a considerable share of the time spent on radiotherapy planning, and a contour proposed by a model can be refined interactively by the clinician. Promptable foundation models such as SAM 3 support this workflow by writing each correction into a session memory that conditions the remaining slices, while the model weights stay fixed. On 690 test cases from five public CT cohorts, fine-tuning SAM 3 on lung tumours raises the Dice obtained from a single point prompt from 0.298 to 0.757, and seven rounds of corrections raise it further to 0.765, but under memory conditioning alone the accuracy on slices the annotator has not touched stops improving after six rounds. We therefore treat each correction as a training signal and propose LeCor, which performs test-time training on a small set of case adapters that are reset for every case and meta-learned such that a single gradient step driven by a click improves the slices that were not clicked. On the 133 test cases that span at least eight slices, LeCor raises the Dice reached after seven correction rounds from 0.787 with the fine-tuned model to 0.827, reduces the number of cases that never reach a Dice of 0.80 from 47 to 27, and reaches in three correction rounds the accuracy that the fine-tuned model attains in seven.

Yi Luo, Yike Guo, Wenxuan Li +3

Department of Biomedical Engineering, Johns Hopkins University · Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University · Department of Computer Science, Johns Hopkins University +1

Radiotherapy Test-Time Training Meta-Learning 3D Generation Prompt Engineering

Sep 1, 2026cs.LG

A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference

The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution of a fixed trained model, a growing body of work studies how models can refine their behavior on the fly by exploiting test-time information and additional computation. These developments have largely evolved along two directions: methods that modify the model's state using test-time signals, and methods that improve predictions through extra inference-time resources such as more sampling and tool use. However, these directions are often studied in separate communities with different terminology, making their connections harder to see. In this survey, we present feedback-driven Test-Time Intelligence (TTI) as a unified perspective for understanding such deployment-time improvement. We use this view to relate test-time adaptation, test-time learning, and test-time scaling, highlighting both their distinctions and their growing overlap in hybrid systems. This unified framework helps connect previously fragmented ideas and provides a clearer conceptual foundation for studying inference-time self-improvement. We review major methodological paradigms, representative applications, and open challenges across vision, language, multimodal learning, generative models, robotics, and healthcare. Our goal is to provide a coherent foundation and research roadmap for the study of self-improving AI systems at test time.

Shuaicheng Niu, Guohao Chen, Yaofo Chen +14

South China University of Technology · Nanyang Technological University · Tulane University +3

Test-Time Adaptation Test-Time Training Inference-Time Recursive Self-Improvement Intelligence Generative Models

Aug 10, 2026cs.RO

VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction

Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams, but it remains difficult to use reliably in closed-loop manipulation. A shared adaptation space can mix incompatible task corrections, while an online update can alter subsequent actions before its consequences are known. We introduce a reliable TTT framework for VLA policies (VANE). VANE conditions prompt adaptation on the current vision--language context and learns from the future visual consequences of executed actions. Candidate updates are isolated from the live policy, evaluated on subsequent observations, and committed only when supported by future evidence, making adaptation selective and reversible. On SimplerEnv WidowX, VANE improves average success by

3.2

percentage points over the corresponding TTT baseline. Results on Google Robot further show that deployment-time gains remain task- and embodiment-dependent. Together, these results demonstrate a constrained, evidence-based approach to adapting VLA policies during interaction.

Hongjin Ji, Guoyang Xia, Luoyang Sun +2

The Chinese University of Hong Kong, Shenzhen · Li Auto Inc. · Beijing University of Posts and Telecommunications +2

Test-Time Training

Aug 7, 2026cs.LG

Modular TTT: Rethinking Test-Time Training as Composable Modules

Test-time training (TTT) views sequence modeling as an online learning problem in which fast weights are updated by an internal learning rule. Despite the growing number of TTT variants, existing approaches typically hard-code each variant separately, which makes it difficult to design new TTT methods and to isolate the role of each component. To address this, we propose Modular TTT, a framework that represents the inner learner as a directed acyclic graph and exposes the fast-weight network, loss function, learning rate, weight decay, and normalization as explicit design dimensions. Modular TTT automatically composes primitive-level train-view forward, train-view backward, and causal query-view rules into the full graph-level TTT computation, including the fast-weight state transition. Using Modular TTT, we systematically ablate the components of TTT and find that small learning-rate initialization, weight decay, and a single-layer nonlinearity improve performance, while MSE and inner-product losses perform similarly. Deeper fast-weight networks and normalization tend to hurt performance because they induce excessively large activations, while residual connections and gating provide little measurable benefit. Guided by these findings, we train the best resulting variant as 410M- and 1.45B-parameter models on 100B tokens, and observe training loss and benchmark performance comparable to Gated DeltaNet.

Bohao Tang, Zhen Qin, Yuqi Pan +3

Shanghai Jiao Tong University · Shanghai Innovation Institute · ByteDance Seed

Test-Time Training Sequence Modeling Batch

Aug 3, 2026cs.CL

Learning What to Remember: Test-Time Training via Context Distillation

Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later. Test-time training (TTT) is an appealing approach that performs online parameter updates for long-context modeling, yet existing TTT methods only optimize either reconstruction or online adaptation objectives without considering the future utility of retained information. In this work, we propose \textbf{T}est-\textbf{T}ime \textbf{C}ontext \textbf{D}istillation (TTCD), a TTT framework that introduces a self-supervised objective for allocating limited memory capacity for future use. Specifically, TTCD uses a long-window teacher to supervise the fast weights of a short-window student, where the hidden-state discrepancy between them offers a dense, self-supervised signal guiding the model to memorize the contextual information crucial for future token predictions. We focus on an in-place variant: In-Place TTCD (IP-TTCD), which uses the existing MLP parameters as the fast weights. Experiments on long-context language modeling tasks show IP-TTCD consistently outperforms DeltaNet, Gated DeltaNet, sliding-window attention, and TTT when pre-trained from scratch. Furthermore, IP-TTCD allows pre-trained transformer models to adapt their parameters during inference through continual pre-training, gaining long-context capabilities with only a lightweight architectural augmentation. Our results position TTCD as a step toward architectural continual learning.

Zixuan Wang, Xingyu Dang, Rui-Jie Zhu +4

Princeton University · UC Santa Cruz · Carnegie Mellon University +1

Efficient Long-Context Inference Test-Time Training Replay-Based Continual Learning Dataset Distillation Generative Pretrained Transformers

Jul 22, 2026cs.CV

Test-Time Training for Modality Order Consistency in Vision-Language Models

We find that vision-language models are sensitive to a specific semantically irrelevant change: the order in which the image and question are presented. Across three models and three benchmarks, image first prompting consistently outperforms question-first prompting, revealing a repeatable modality order failure. We use this gap to design an order-consistent test-time training method. Our method substantially closes the modality-order gap across all evaluated settings. Surprisingly, it also yields consistent improvements in the stronger image-first branch over the baseline, hence bootstrapping both orderings toward mutual consistency. Activation patching localizes the ordering failure to a narrow mid-network region where representations diverge sharply between prompt orders. We find that the test-time training method repairs this misalignment across layers. Together, our results identify modality-order sensitivity as a circuit-level failure in VLMs and demonstrate that simple, asymmetric test-time adaptation can effectively mitigate it and even improve performance over the baseline.

Aditi Gupta, Yossi Gandelsman

University of Chicago · Reve

Modalities Test-Time Training Order

Jul 10, 2026cs.CL

Self-Guided Test-Time Training for Long-Context LLMs

Long-context processing has become increasingly important for large language models (LLMs), but simply extending the context window does not guarantee effective utilization of long inputs. As input length grows, accuracy often degrades, indicating that models still struggle to identify and use the evidence most relevant to a question. A promising way to improve long-context utilization is test-time training (TTT), which treats the test context as a training example for instance-specific parameter adaptation. However, applying TTT to the entire long context is prohibitively expensive, while adapting on randomly sampled spans introduces severe noise. Because most spans in a long context are irrelevant to the specific question, training on them may even degrade the base model's performance. Our preliminary study shows that TTT is highly sensitive to training-span quality: on LongBench-v2, TTT on randomly sampled spans hurts performance, whereas TTT on oracle spans substantially improves it. Motivated by this, we propose a simple method, Self-Guided TTT (S-TTT): before adaptation, the model identifies the evidence spans it should learn from, and the standard language-modeling training objective is applied only to those selected spans. On two challenging long-context reasoning benchmarks, LongBench-v2 and LongBench-Pro, S-TTT improves accuracy for both Qwen3-4B-Thinking-2507 and Llama-3.1-8B-Instruct, achieving up to a 15% relative improvement.

Xinyu Zhu, Zhe Xu, Xiaohan Wei +10

Meta AI · University of Virginia

Efficient Long-Context Inference Test-Time Training Large Language Model Training Reasoning Benchmark Oracles

Jul 3, 2026cs.LG

No Time Like the Present: Agentic Test-Time Training for LLM Agents

LLM agents often degrade over long episodes: as trajectories grow, they revisit explored states, repeat failed actions, and lose strategies that previously worked. Test-time training (TTT) offers a way to adapt model weights to the evolving task state, but existing LLM TTT methods largely adapt once to a fixed input. We study continuous TTT in multi-turn agent episodes, where each update changes the policy that generates later training text. This creates a self-training loop that helps when new trajectory information appears, but can amplify drift when the agent gets stuck and repeatedly trains on similar text. We find that update-text repetition distinguishes these regimes and introduce Agentic Test-Time Training (aTTT), a token-level reweighting method that downweights the loss on tokens appearing in repeated

n

-grams from prior updates while leaving novel tokens fully weighted. To run such updates inside live episodes, we build a concurrent serving system using vLLM's runtime LoRA API, limiting overhead to 1.9

\times

the no-TTT cost. aTTT improves success by up to 5.0 points on ALFWorld and 4.9 points on SWE-bench Lite. The gains concentrate where models already have task competence but drift over long trajectories, suggesting that aTTT mainly preserves existing competence rather than teaching new abilities.

Yanbo Wang, Jinhua Hao, Yuze Shi +2

Kuaishou Technology

Test-Time Training Large Language Model Training Test-Time Scaling

Jul 1, 2026cs.CL

Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training

Large language model test-time training (TTT) is often evaluated through local proxy metrics: models are updated on recent tokens, retrieved context, target-domain data, or verifiable task attempts, and then judged by perplexity, future-token loss, long-context performance, or reward. These metrics are well matched to claims about stream adaptation, domain adaptation, context compression, and reward-backed test-time improvement. They are weaker evidence, however, for a capability that TTT results are increasingly used to motivate: deployed assistant memory, personalization, or sparse post-deployment learning, which instead requires behavioral evidence such as later recall, paraphrase robustness, retention, locality, conflict handling, and use in downstream actions after the original support context is removed. We introduce a behavioral evaluation framework that calibrates TTT memory claims to the evidence that supports them. It has two components: a claim-calibrated evidence ladder that separates stream/domain adaptation, bridge internalization, and deployment-time behavioral learning; and an evaluation protocol with matched explicit-memory baselines and mutually exclusive failure categories. We validate the framework by auditing recent TTT and memory-adjacent work and by instantiating it as a controlled diagnostic in which, in a sparse nonce-fact setting, one-step LoRA updates lower support and answer loss across three Qwen3 model scales while generated free-form recall stays at zero, exposing a measurable gap between proxy improvement and deployment behavior. The framework gives authors and evaluators a concrete standard for aligning TTT memory claims with the evidence actually reported.

Xiangchen Song, Zhenhao Chen, Lingjing Kong +4

Carnegie Mellon University · MBZUAI

Large Language Model Memory Large Language Model Evaluation Test-Time Training Post-Deployment Adaptation Large Language Model Training Test Time+1

Jun 29, 2026cs.LG

T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation

Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, often leading to degraded performance under distribution shifts. This issue can be mitigated by conventional fine-tuning, but in many real-world cases, collecting labeled data is expensive or infeasible. A potential approach is Test-Time Training (TTT), which adapts models' weights using unlabeled test data, yet it is typically limited to shallow updates that affect only a subset of model parameters. We propose T3R, leveraging multiple Rotograd matrices to improve task affinity between the target and auxiliary tasks, essential for effective test-time training. T3R further introduces a rotation technique that reorients self-supervised signals using these matrices to create surrogate gradients for the target task, allowing deeper adaptation across nearly the entire architecture. Empirically, T3R reduces MAE by 0.172 points over standard inference in regression datasets and achieves at least 9.37% relative improvement on cross-domain OGB classification benchmarks compared to models without adaptation. These results highlight the potential to develop an adaptation pipeline for graph-based systems, particularly in settings where conventional fine-tuning or retraining is infeasible.

Huy Truong, Alexander Lazovik, Victoria Degeler

Bernoulli Institute, University of Groningen, Groningen, The Netherlands · Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands

Stable Test-Time Adaptation Graph Neural Networks Test-Time Training

Jun 25, 2026cs.CV

Forget, Anticipate and Adapt: Test Time Training for Long Videos

Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during inference. This procedure does not require labels at test-time. This paper focuses on TTT for long-videos. A major concern with existing approaches is: 1) they perform TTT updates using a sliding window containing frames in the past, whose compute increases linearly with the size of window. This becomes computationally intractable when the videos are hours long. 2) TTT is performed even when temporally close frames look similar, thereby consuming a lot of compute. We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos.

Rajat Modi, Sebastian Noel, Xin Liang +1

Institute of Artificial Intelligence, University of Central Florida

Test-Time Training Video Temporal Grounding Long Videos Catastrophic Forgetting Forgetting Anticipate

Jun 24, 2026cs.CV

Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs

While test-time adaptation (TTA) empowers vision-language models to adapt without costly retraining, it remains highly vulnerable to out-of-distribution (OOD) outliers prevalent in real-world applications. This discrepancy motivates Noisy TTA (NTTA), an online task to filter noisy OOD samples on the fly while maximizing in-distribution (ID) classification accuracy. Existing zero-shot NTTA approaches typically rely on test-time discriminative training, leading to overconfident misclassifications and significantly degraded inference efficiency. To address these limitations, we propose a novel framework named Dual Distribution Estimation (DDE), shifting the zero-shot NTTA paradigm from instance-level learning to training-free Gaussian distribution modeling. DDE incorporates two novel modules: Positive Feature Distribution Estimation (PFDE) and Negative Label Distribution Estimation (NLDE). PFDE explicitly models class-wise inclusion and exclusion Gaussian distributions to formulate a calibrated contrastive score, robustly enhancing ID accuracy. In parallel, NLDE improves OOD identification by explicitly modeling the negative label distribution to mine highly discriminative labels, effectively mitigating spurious correlations. Extensive experiments show that on the large-scale ImageNet benchmark, DDE achieves an improvement of 3.70% in harmonic mean accuracy and reduces the FPR95 for OOD detection by 6.20%, while ensuring highly scalable and efficient online inference. Furthermore, DDE is zero-shot and training-free, demonstrating remarkable robustness in data-scarce scenarios. Codes are available at https://github.com/ZhuWenjie98/DDE.

Wenjie Zhu, Yabin Zhang, Liang Xu +3

The Hong Kong Polytechnic University · Harbin Institute of Technology (Shenzhen) · Shanghai Jiao Tong University +1

Out-Of-Distribution Detection Vision-Language Model Adaptation Test-Time Adaptation Test-Time Training Fast Inference Negative Results

Jun 19, 2026cs.CL

Test-Time Training with Next-Token Prediction

Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test time. We study whether this signal can define the inner-loop objective for test-time training (TTT) in pretrained long-context language models. Many TTT architectures require models to be trained with test-time adaptation in mind, limiting their direct applicability to released LLM checkpoints. While recent in-place TTT methods make fast-weight adaptation possible for pretrained LLMs without redesigning the backbone, they leave a central question unresolved: what should each test-time write store? Existing recipes train the fast weight to match a learned local value proxy but they are not directly tied to the self-supervised next-token prediction signal. We introduce Test-Time Training with Next-Token Prediction (TTT-NTP), a drop-in fast-weight adaptation method for pretrained LLMs that instead supervises updates using the model's own next contextual hidden state. This makes each local write follow the same causal computation that supports next-token prediction: the value target is a pointwise linear projection of a single next-position contextual state. On RULER Full-13, averaged over 4k to 32k contexts, TTT-NTP is the only method that consistently improves the released backbone across four models spanning three families and a 0.6-8B size range, by 3.9 points on Llama-3.1-8B, 3.0 on Mistral-7B-v0.3, 4.1 on Qwen3-4B, and 2.9 on Qwen3-0.6B. On the real-world LongBench-v2 long-document QA benchmark, TTT-NTP improves over the base model by 5.6 points on Llama-3.1-8B and 3.7 on Mistral-7B-v0.3, while preserving commonsense and knowledge performance. Our code is publicly available at https://github.com/yancyou/TTT-NTP.

Xuan Ouyang, Zefan Cai, Junjie Hu

University of Wisconsin–Madison

Test-Time Training Next-Token Prediction Autoregressive Token Prediction Test-Time Adaptation Model Checkpoints

Jun 19, 2026cs.LG

MedTS-TTT: Test-Time Training for Medical Time Series Classification

Medical time series (MedTS) signals such as electroencephalography (EEG) and electrocardiography (ECG) support many clinical applications. However, substantial subject-level heterogeneity often induces subject-level distribution shift, causing a fixed parameter set to generalize poorly to unseen individuals. Compared with domain adaptation methods that often depend on extra adaptation components or target-batch statistics, Test-Time Training (TTT) provides a more practical solution for sequential clinical data by enabling online adaptation from unlabeled test samples. However, many representative TTT methods require iterative inner-loop optimization, increasing test-time overhead. In this paper, we propose MedTS-TTT, a test-time training framework for medical time series modeling. MedTS-TTT is built upon Closed-Loop Self-Alignment Test-Time Training (CLSA-TTT) and a Gated Convolutional Backbone (GCB). CLSA-TTT constructs a token-level self-supervised target and performs a single-step fast-weight update for intra-layer closed-loop alignment, enabling rapid sample-wise adaptation without iterative inner-loop optimization. GCB combines CLSA-TTT-based fast adaptation and token-level fusion with a gated convolutional branch to balance local dynamic modeling and information-flow control. On 4 public datasets (2 EEG and 2 ECG) with subject-independent splits, MedTS-TTT achieves 11 top-1 rankings out of 12 evaluations across 9 baselines and 3 metrics. The code is publicly available at https://github.com/mingzhi-c/MedTS-TTT.

Mingzhi Chen, Yiyu Gui, Guibo Luo

Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University, Shenzhen, China

Time-Series Classification Test-Time Training Time Series Electroencephalography Time-Frequency Distribution Shifts

Jun 16, 2026cs.CV

Test-Time Training for Robust Text-Guided Open-Vocabulary Object Counting

Text-guided Open-vocabulary Object Counting (TOOC) enables counting arbitrary object categories specified by text prompts, offering substantially greater flexibility than conventional closed-set counting. However, existing TOOC methods are developed and evaluated primarily on ideal images, while real-world scenes often suffer from adverse conditions such as rain, fog, darkness, and sensor noise, which severely degrade visual quality and impair vision-language alignment. To bridge this gap, we introduce Robust-TOOC, the first benchmark for evaluating TOOC under diverse corruption conditions, which covers six representative degradation types: rain, fog, darkness, Gaussian noise, salt-and-pepper noise, and mixed corruption. To improve robustness while preserving the original counting architecture, we propose Dual-TTT, a dual-architecture test-time training framework for TOOC. Specifically, during test-time training, Dual-TTT updates only the Text-guided Lightweight Denoising module (TL-Denoiser), while keeping the original counting network frozen. Inspired by diffusion models, the TL-Denoiser is optimized to remove corruption-aware noise from image representations under degraded conditions. Since only the TL-Denoiser is trained at test time, Dual-TTT is annotation-free and can be seamlessly integrated into existing TOOC models without modifying their original architecture. Extensive experiments on multiple recent TOOC baselines demonstrate the effectiveness of our method.

Hao-Yuan Ma, Yuda Zou, Li Zhang +1

School of Computer Science and Technology, Soochow University Suzhou, China · Wuhan University Wuhan, China

Open-Vocabulary Object Detection Scene Text Recognition Counting Test-Time Training Iterative Denoising Methods Duality

Jun 14, 2026cs.LG

A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt

Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts. Yet, its performance often suffers from instability and sensitivity to hyperparameters such as update steps and subspace. We explain this behavior through a decision-theoretic lens, treating TTT as implicit Bayesian inference in the kernel regime. Under a Gaussian process benchmark, we show that TTT reduces prediction error when updates are spectrally matched to the prompt's signal-to-noise ratio and aligned with query-relevant eigen-directions. This perspective underpins the following results: (1) we show when fixed update steps and subspaces fail under distribution shifts, motivating adaptive strategies; (2) we prove that selecting update steps via prompt evidence admits a PAC-Bayes guarantee against overfitting; and (3) we characterize the Bayes-optimal update subspace under a linear-Gaussian correction model, yielding a scoring rule for selecting Transformer blocks and heads. Our theory helps explain the empirical instability of TTT, taking a step toward principled guidance for when, how far, and which directions to adapt.

Tomoya Wakayama

RIKEN Center for Advanced Intelligence Project (AIP), Tokyo, Japan.

Stable Test-Time Adaptation Test-Time Training Distribution Shifts Gaussian Process

Jun 9, 2026cs.DS

The Power of Test-Time Training for Approximate Sampling

Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the rise of generative AI, as sophisticated sampling procedures from LLMs have been proposed to solve challenging reasoning problems. The efficacy of such sampling algorithms is limited, however, by the relationship between the LLM and the particular sampling task at hand, which has motivated the framework of test-time training (TTT). TTT works by updating a model's weights in response to partial generations and reward feedback received at inference time, thus adapting to the particular problem. In this work, we propose a formalization for TTT as the problem of producing a sample from a given probability measure

μ^\star

belonging to a known class

{F}

of distributions, given an oracle

\hat μ

which yields approximate density estimates for

μ^\star

. This is closely related to the problem of reducing sampling to approximate counting studied in seminal works of Jerrum, Valiant & Vazirani (1986) and Jerrum & Sinclair (1989): namely, when

{F}

is the class of all distributions, it coincides exactly with the aforementioned counting-to-sampling reduction. In this paper, we first show a quadratic lower bound on the query complexity of sampling from

μ^\star

given query access to

\hat μ

(for sufficiently large classes

{F}

), thus showing that the random walk approach proposed by Jerrum & Sinclair (1989) and refined by Hayes & Sinclair (2010), is optimal. This answers an open question posed by Hayes & Sinclair. We then show that this lower bound can be circumvented if the size of

{F}

is bounded appropriately. As we discuss, this latter result can be viewed as an abstraction of TTT, and thus represents a starting point for the development of a principled theoretical framework for TTT.

Noah Golowich, Ankur Moitra, Dhruv Rohatgi

Microsoft Research NYC · MIT

Optimal Sample Complexity Test-Time Training Inference-Time Generative Artificial Intelligence

Jun 9, 2026cs.CV

U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training

Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restricting their robust clinical deployment. This lack of generalization stems from the conventional paradigm of fixed-parameter models that cannot adapt to variations in test data (e.g., dose levels or scanner types) after training. To overcome this limitation and achieve robust generalization, we introduce U-TTT, a novel U-shaped model that integrates Test-Time Training (TTT) layers to dynamically adjust model parameters during inference through self-supervision, thereby adapting to the specific characteristics of each test instance. Furthermore, to comprehensively capture the complex degradations of 3D PET data, U-TTT features a dual-domain adaptation mechanism comprising a Spatial Test-Time Training (S-TTT) layer and a Frequency Test-Time Training (F-TTT) layer. The S-TTT layer captures and corrects spatial structural degradations, while the F-TTT layer suppresses global noise spectra and restores delicate high-frequency details. Extensive experiments demonstrate that U-TTT achieves state-of-the-art PET denoising performance and exhibits superior generalization under challenging distribution shifts, including both unseen dose levels and unseen scanners. Our code will be available at https://github.com/Yaziwel/U-TTT.

Zhiwen Yang, Jiayin Li, Hao Lu +3

School of Biological Science and Medical Engineering, Beihang University, Beijing 100191, China · Department of Biomedical Engineering, Tsinghua University, Beijing 100084, China · School of Aerospace Engineering, Tsinghua University, Beijing 100084, China

Positron Emission Tomography U-Net Test-Time Training

Jun 7, 2026cs.CL

From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory

Large language model (LLM) agents are increasingly deployed in long-running settings where improving through experience at test time becomes important. A common approach is to update an explicit memory after each interaction to guide future decisions. However, most existing methods rely on hand-designed prompting rules, making it difficult to align memory updates with downstream objectives over multi-step horizons consistently. We propose MemoPilot, a plug-in memory copilot that explicitly trains the memory update process to improve a frozen LLM's performance across sequential interactions. We formulate memory updating as a multi-turn decision problem and optimize it end-to-end with multi-turn GRPO. Our training recipe introduces (i) a turn-wise reward signal and (ii) a context-independent, turn-level advantage estimation across rollouts, enabling finer-grained credit assignment and more stable training in multi-turn settings. We evaluate MemoPilot on two testbeds: multi-round Rock-Paper-Scissors (RPS) and Limit Texas Hold'em (LHE). Across both environments, MemoPilot substantially improves test-time learning of a frozen player over strong baselines, ranking first in Elo ratings on both games (1762 on LHE and 1590 on RPS) and outperforming all baseline memory methods and proprietary models, including DeepSeek-V3.2.

Yishuo Cai, Xingyu Guo, Xuancheng Huang +8

Peking University, Beijing, China · Central South University, Changsha, China · Zhipu AI, Beijing, China +3

Large Language Model Agents Test-Time Training Step-Level Advantage Estimation Pilot

Jun 5, 2026cs.CL

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering

Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input. Existing within-context retrieval methods localize and expose candidate evidence chunks for the question, but they stop at input-level evidence exposure rather than adapting the query-side attention parameters that control how the model allocates attention over full-context positions. In contrast, lightweight test-time adaptation methods, such as query-only test-time training (qTTT), leave evidence localization unresolved because their generic span-level self-supervised objectives do not identify which context positions support the current answer. In this paper, we propose Evidence-Aligned SElective Test-Time Training (EASE-TTT), a within-context retrieval-augmented test-time training framework that converts selected evidence chunks into a soft attention supervision target over their token positions. Instead of replacing the full context with retrieved chunks, EASE-TTT uses the resulting attention target to guide query-side adaptation, with the adapted model generating the final answer from the original full context. Experiments on six LongBench QA tasks and three small decoder-only language models show that EASE-TTT achieves the strongest macro-average performance among full-context inference, retrieval-only baselines, and qTTT, supporting evidence-aligned test-time adaptation in long-context QA.

Xiaopeng Yuan, Zebin Wang, Suwen Wang +3

University of Illinois Urbana-Champaign · 2Harvard University · 3Brion, ASML US LP +1

Efficient Long-Context Inference Question-Answering Benchmarks Long-Context Reasoning Test-Time Training Qwen3 Question

Jun 3, 2026cs.LG

Alpha-RTL: Test-Time Training for RTL Hardware Optimization

Large language models (LLMs) have shown increasing promise in generating functionally correct register-transfer-level (RTL) hardware designs. Recent systems improve further through EDA-integrated reinforcement learning with syntax, simulation, and PPA rewards, but train a general RTL generator before deployment while test-time approaches search with a frozen policy. We instead perform reinforcement learning at test time, allowing the LLM policy to adapt to executable EDA feedback for the specific RTL problem at hand. We propose TTT-RTL, to our knowledge the first per-design test-time training framework that closes the loop between an LLM policy and an EDA pipeline for RTL optimization. TTT-RTL samples candidate implementations, verifies them through syntax checking and simulation, scores valid designs using synthesis-derived PPA product, reuses high-reward variants through a PUCT-indexed design-state pool, and updates the policy with an entropic policy-gradient objective. To stabilize policy updates under sparse or plateaued rewards, we introduce an adaptive KL-budget controller that adjusts the entropy constraint using reference KL, effective sample size, and reward saturation signals. On RTLLM v2.0 under Nangate 45nm, TTT-RTL reduces the geometric-mean PPA product by 65.1% over the reference, outperforming the strongest published frozen-policy agent baseline at 26.1%. On an industrial XuanTie C910 FPU leading-zero-anticipation unit under Sky130, TTT-RTL achieves a 59.4% ADP reduction, and ablations confirm that policy adaptation, state reuse, and KL-budget control each contribute. These results suggest that test-time training with executable EDA feedback can move LLM-based RTL generation beyond functional correctness toward physically optimized hardware.

Peilong Zhou, Zhirong Chen, Cangyuan Li +4

1SKLP, Institute of Computing Technology, Chinese Academy of Sciences · University of the Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences

Hierarchical Register Transfer Level Generation Register Transfer Level Test-Time Training Invariant Synthesis

Jun 2, 2026cs.RO

TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models

Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time. Recent VLA models suggest that prompts can serve as an efficient interface for steering policy behavior, but existing prompt-based steering typically relies on external guidance. This raises a natural question: can test-time training (TTT) for VLA be achieved by optimizing a prompt, so that the steering interface itself can be learned and adapted from interaction? We address this question with TTT-VLA, a test-time training framework based on Latent Prompt Optimization (LPO). During training, the latent prompt is learned with an additional proxy task, providing an extra learned conditioning signal for policy learning. At test time, TTT is performed by collecting interaction data from the current environment and optimizing only the latent prompt on those data using the proxy task's self-supervised signal, without modifying the policy itself. Experiments on SimplerEnv demonstrate that the proposed method consistently improves task success rates in both single- and multi-embodiment settings. Further analysis shows that the gains arise primarily from correcting a small number of critical decisions rather than globally altering policy behavior. These results suggest that LPO provides an effective and practical pathway for deployment-time improvement of foundation manipulation policies.

Wenbo Zhang, Jianxiong Li, Shuai Yang +4

ByteDance Seed · The University of Adelaide · Tsinghua University +3

Test-Time Training Steering

May 31, 2026cs.IR

Test-Time Training for Zero-Resource Dense Retrieval Reranking

Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings. Existing approaches face a fundamental dilemma: cross-encoders deliver strong reranking quality but require costly supervised training and incur high latency, while unsupervised BM25 reranking consistently degrades dense retrieval performance on most of BEIR benchmarks. We propose DART (Dense Adaptive Reranking at Test-time), which resolves this dilemma by adapting the scoring function at inference time. For each query, the top-ranked documents serve as pseudo-positive examples and the bottom-ranked as pseudo-negative examples, providing noisy but readily available supervision to adapt a bilinear scoring matrix

W

via a small number of gradient updates. We further introduce a confidence-weighted margin loss and a cross-query momentum buffer that warm-starts adaptation across queries. On six BEIR benchmarks, DART achieves a mean per-dataset relative NDCG@10 gain of +2.1% over the dense retrieval baseline with under 10ms additional latency per query, demonstrating a powerful capability for zero-shot performance enhancement and cross-domain generalization.

Shiyan Liu, Yichen Li

Huazhong University of Science and Technology · ByteDance

Retrieval Layer Cross-Encoder Reranking Reranking Cross-Encoder Dense Zero-Shot Robustness+1

May 28, 2026cs.LG

Test Time Training for Supervised Causal Learning

Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution generalization challenges. We reveal three limitations of previous SCL practices: a significant performance gap between synthetic benchmarks and real-world data, fragility to distribution shifts, and failure in compositional generalization, collectively questioning its real-world applicability. To address this, we propose Test-Time Training for Supervised Causal Learning (TTT-SCL), a novel framework that dynamically generates training sets explicitly aligned with any specific test instance. We demonstrate the correlation between TTT-SCL and score-based methods, and design an efficient module for generating training sets based on the classic scoring function. Experiments on synthetic benchmarks, pseudo-real and real-world datasets demonstrate that TTT-SCL significantly outperforms existing SCL and traditional causal discovery methods.

Zizhen Deng, Jiaru Zhang, Rui Ding +5

Peking University · The work was done during his internship at Microsoft. · Shanghai Jiao Tong University +2

Causal Discovery Methods Test-Time Training Out-Of-Distribution Causal Attention Synthetic Benchmark

May 27, 2026cs.LG

RW-TTT: Batched Serving for Request-Owned Test-Time Training State

Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights: serial execution is correct but slow, while naive batching can corrupt request state. We formulate this problem as read-write TTT serving and present RW-TTT , which tags each decode step with its owner, version, and READ/WRITE effect, batches only compatible phases, and commits updates only to the owner. On one GPU with eight fast-weight InPlace-TTT streams, RW-TTT reaches 274.61 aggregate tok/s, 9.31x over sequential serving and 3.44x over per-stream replicas under the same memory budget. It preserves behavior on RULER, a long-context benchmark, and passes owner/version checks.

Jian Yang, Zhizhuo Kou, Yao Tian +4

1The Hong Kong University of Science and Technology · 2The Chinese University of Hong Kong · 3National University of Singapore

Large Language Model Serving Time-To-First-Token Test-Time Training Streaming

May 21, 2026cs.LG

Test-Time Training Undermines Safety Guardrails

Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this dynamic adaptation introduces new vulnerabilities that adversaries can exploit to jailbreak models. We identify three threat models for TTT and demonstrate how attackers can leverage them to bypass safety filters. Our results show that TTT can significantly increase the Attack Success Rate (ASR) and the ASR over 10 generation trials (ASR@10). For example, under LoRA, the few-shot and generation-phase threat models achieve an average ASR@10 of 95% and 93% respectively, across models from different families and scales. These vulnerabilities transfer to production fine-tuning APIs. We also show that TTT-induced overfitting can produce degenerate outputs that inflate ASR under standard judges, and propose a validity-aware evaluation to correct for this. Our findings suggest that TTT exposes a new attack surface, strengthens attacks, and undermines existing safety guardrails. As a first step toward defense, we propose a lightweight provider-side detector that flags TTT requests via the perplexity shift on a private harmful holdout, but robust deployment will ultimately require dynamic alignment.

Simone Antonelli, Sadegh Akhondzadeh, Aleksandar Bojchevski

CISPA Helmholtz Center for Information Security · University of Cologne

Inference-Time Defense Test-Time Training Realistic Threat Model Attack-Success Rate Guardrail Overfitting

May 14, 2026cs.LG

Test-Time Learning with an Evolving Library

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model parameters, our approach maintains a shared library of knowledge abstractions, including modular skills and reflective insights, automatically extracted from the model's own inference trajectories. To support continual improvement, we introduce a principled weighting and consolidation mechanism that jointly optimizes for immediate utility and long-term value. This allows simple, instance-specific abstractions to evolve into more general and reusable ones over time. Across challenging benchmarks in mathematical reasoning, code generation, and multi-turn agentic environments, EvoLib improves substantially over the top test-time scaling and learning methods without ground-truth feedback.

Weijia Xu, Alessandro Sordoni, Chandan Singh +4

Microsoft Research

Test-Time Training Replay-Based Continual Learning Code Generation

May 13, 2026cs.CL

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks. In this work, we study many-shot ICL on reasoning tasks, with a particular focus on many-shot chain-of-thought in-context learning (CoT-ICL). Analyzing across non-reasoning and reasoning tasks and across non-reasoning and reasoning-oriented LLMs, we identify several distinctive properties of many-shot CoT-ICL. We further interpret these findings by viewing many-shot CoT-ICL as in-context test-time learning rather than scaled pattern matching, and suggest two principles: (i) demonstrations should be easy for the target model to understand, and (ii) they should be ordered to support a smooth conceptual progression. Guided by the principle, we propose Curvilinear Demonstration Selection (CDS), a simple ordering method that yields up to a 5.42 percentage-point gain on a math task with 64 demonstrations. Overall, our results reframe the long context window from a retrieval buffer into a structured curriculum for in-context test-time learning.

Tsz Ting Chung, Lemao Liu, Mo Yu +1

Hong Kong University of Science and Technology · Fudan University · Wechat AI, Tencent.

In-Context Learning In-Context LLM Reasoning Strategies Instruction-Tuned Models Reasoning Skills Test-Time Training

May 13, 2026cs.CL

Query-Conditioned Test-Time Self-Training for Large Language Models

Large language models (LLMs) are typically deployed with fixed parameters, and their performance is often improved by allocating more computation at inference time. While such test-time scaling can be effective, it cannot correct model misconceptions or adapt the model to the specific structure of an individual query. Test-time optimization addresses this limitation by enabling parameter updates during inference, but existing approaches either rely on external data or optimize generic self-supervised objectives that lack query-specific alignment. In this work, we propose Query-Conditioned Test-Time Self-Training (QueST), a framework that adapts model parameters during inference using supervision derived directly from the input query. Our key insight is that the input query itself encodes latent signals sufficient for constructing structurally related problem--solution pairs. Based on this, QueST generates such query-conditioned pairs and uses them as supervision for parameter-efficient fine-tuning at test time. The adapted model is then used to produce the final answer, enabling query-specific adaptation without any external data. Across seven mathematical reasoning benchmarks and the GPQA-Diamond scientific reasoning benchmark, QueST consistently outperforms strong test-time optimization baselines. These results demonstrate that query-conditioned self-training is an effective and practical paradigm for test-time adaptation in LLMs. Code is available at https://chssong.github.io/Query-Conditioned-TTST/.

Chaehee Song, Minseok Seo, Yeeun Seong +2

School of Electrical Engineering, KAIST · 2Graduate School of Green Growth and Sustainability, KAIST

Test-Time Training Test-Time Scaling

May 7, 2026cs.LG

PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents

Large language models have become drivers of evolutionary search, but most systems rely on a fixed, prompt-elicited policy to sample next candidates. This limits adaptation in practical engineering and research tasks, where evaluations are expensive, and progress depends on learning task-specific search dynamics. We introduce PACEvolve++, an advisor-model reinforcement learning framework for test-time policy adaptation in evolutionary search agents. PACEvolve++ decouples strategic search decisions from implementation: a trainable advisor generates, assesses, and selects hypotheses, while a stronger frontier model translates selected hypotheses into executable candidates. To train the advisor under non-stationary feedback, we propose a phase-adaptive approach that adapts its optimization strategy to different phases of the evolutionary process. Early in evolution, it uses group-relative feedback to learn broad search preferences; later, as reward gaps compress, it emphasizes best-of-

k

frontier contribution to support stable refinement. Across expert-parallel load balancing, sequential recommendation, and protein fitness extrapolation, PACEvolve++ outperforms the state-of-the-art evolutionary search framework with frontier models, achieving faster convergence and stabilizing test-time training during evolutionary search.

Minghao Yan, Bo Peng, Benjamin Coleman +11

1Google · University of Wisconsin–Madison · 3Google DeepMind

Evolutionary Search Test-Time Training

May 6, 2026cs.CV

Test-Time Training for Visual Foresight Vision-Language-Action Models

Visual Foresight VLA (VF-VLA) has become a prominent architectural choice in the recent VLA due to its impressive performance. Nevertheless, the inherent design of VF-VLA makes it particularly vulnerable to out-of-distribution (OOD) shifts. Because the quality of action directly depends on the accuracy of the predicted future visual information, OOD conditions affect both stages at once. To address this vulnerability, we propose Test-Time Training Visual Foresight VLA (

T^3

VF), a test-time training approach motivated by the observation that the predicted future image and its subsequent observation form a natural supervision pair. To further address the practical challenges that arise from indiscriminate test-time updates, we introduce an adaptive update filtering mechanism. Empirically,

T^3

VF mitigates the OOD vulnerability of VF-VLA at a modest additional inference cost, without requiring any architectural modification or auxiliary modules.

Sangwu Park, Wonjoong Kim, Yeonjun In +3

KAIST, Seoul, South Korea.

Diffusion-Based Vision-Language-Actions Photometric Supervision Test-Time Training Out-Of-Distribution Test Time

May 4, 2026cs.CV

Linearizing Vision Transformer with Test-Time Training

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained Transformers provides an appealing shortcut, yet the fundamental representational gap between Softmax and linear attention prevents effective weight transfer. In this work, we address this conversion challenge from two perspectives: architectural alignment and representational alignment. We identify Test-Time Training (TTT) as a linear-complexity architecture whose two-layer dynamic formulation is structurally aligned with Softmax attention, enabling direct inheritance of pretrained attention weights. To further align representational properties, including key shift-invariance and locality, we introduce key instance normalization and a lightweight locality enhancement module. We validate our approach by linearizing Stable Diffusion 3.5 and introduce SD3.5-T

^5

(Transformer To Test Time Training). With only 1 hour of fine-tuning on 4

\times

H20 GPUs, SD3.5-T

^5

achieves comparable text-to-image quality to the fine-tuned Softmax model, while accelerating inference by 1.32

\times

and 1.47

\times

at 1K and 2K resolutions. Code is available at https://github.com/LeapLabTHU/Transformer-to-TTT.

Yining Li, Dongchen Han, Zeyu Liu +3

Tsinghua University, Beijing, China

Self-Supervised Vision Transformers Vision Transformer Diffusion Transformers Linear Attention Transformer Architectures Test-Time Training+1

May 1, 2026cs.LG

Multi-Perspective Transformers in ARC-AGI-2 Challenge

ARC-AGI-2 is a benchmark of human-intuitive visual puzzles that measures a machine's ability to generalize from limited examples, interpret symbolic meaning, and flexibly apply rules in varying contexts. In this paper, we discuss our approach to solving the ARC-AGI-2 puzzles with TinyLM, with additional fine-tuning at test time, including Test-Time-Training (TTT) and Products of Experts (POE). Our model achieves 96.1% accuracy on the training set and 21.7% accuracy on the evaluation set.

Caleb Talley, Vedant Tibrewal, Seun Adekunle +3

Puzzle Model Fine-Tuning Detection Transformer Test-Time Training Challenges

Apr 22, 2026cs.LG

Absorber LLM: Harnessing Causal Synchronization for Test-Time Training

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history into states with fixed size and thus lose long-tail dependencies, while methods that memorize contexts into parameters, such as Test-Time Training (TTT), are prone to overfitting token-level projection and fail to preserve the causal effect of context in pretrained LLMs. We propose Absorber LLM, which formulates long-context retention as a self-supervised causal synchronization: after absorbing historical contexts into parameters, a contextless model should match the original model with full context on future generations. We optimize this objective by synchronizing internal behaviors of the updated model with the original one, ensuring context absorption and generalization. Experiments on long-context and streaming benchmarks show that Absorber LLM reduces inference memory and improves accuracy over prior parameter-as-memory baselines.

Zhixin Zhang, Shabo Zhang, Chengcan Wu +2

1Peking University.

Efficient Long-Context Inference LLM Inference Optimization Test-Time Training Retention

Apr 21, 2026cs.LG

TEMPO: Scaling Test-time Training for Large Reasoning Models

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau quickly and do not benefit from additional test-time compute. Without external calibration, the self-generated reward signal increasingly drifts as the policy model evolves, leading to both performance plateaus and diversity collapse. We propose TEMPO, a TTT framework that interleaves policy refinement on unlabeled questions with periodic critic recalibration on a labeled dataset. By formalizing this alternating procedure through the Expectation-Maximization (EM) algorithm, we reveal that prior methods can be interpreted as incomplete variants that omit the crucial recalibration step. Reintroducing this step tightens the evidence lower bound (ELBO) and enables sustained improvement. Across diverse model families (Qwen3 and OLMO3) and reasoning tasks, TEMPO improves OLMO3-7B on AIME 2024 from 33.0% to 51.1% and Qwen3-14B from 42.3% to 65.8%, while maintaining high diversity.

Qingyang Zhang, Xinke Kong, Haitao Wu +7

Tianjin University · Tongyi Lab, Alibaba Group · The Chinese University of Hong Kong +1

Test-Time Training Inference-Time Large Reasoning Models Recalibration

Apr 1, 2026cs.LG

Meta-TTL: Meta-Learning Self-Improvement Policies for Language Agents

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is a self-improvement policy that updates the actor policy based on experience from previous episodes, thereby improving future behavior. Existing methods rely on hand-crafted self-improvement rather than optimizing them for downstream improvement. We argue that optimal self-improvement policies should be learned from task environments, not hand-engineered based on human intuition. To achieve this, we introduce \textbf{Meta-TTL}, a framework that formulates the discovery of effective self-improvement policies as a bi-level optimization problem. Within this framework, the inner loop executes the standard TTL process, measuring how effectively a candidate self-improvement policy helps an agent correct errors across sequential episodes. Guided by the agent's performance, the outer loop performs reflective meta-training across diverse training tasks, using a balanced improvement score (BIS) to balance task contributions during candidate selection. We evaluate Meta-TTL on Jericho, WebArena-Lite, and -bench across both in-distribution (ID) and out-of-distribution (OOD) settings. Meta-TTL consistently outperforms existing baselines, improving TTL over the strongest baseline by up to 23% on ID tasks and 27% on OOD tasks. These results suggest that the optimized self-improvement policy encodes transferable meta-strategies that generalize beyond the training task distribution.

Zhanzhi Lou, Hui Chen, Yibo Li +2

National University of Singapore

Stable Test-Time Adaptation Test-Time Training Single-Agent Baselines Meta

Feb 6, 2026cs.CL

TTSR: Test-Time Self-Evolving via Reflection

Test-time training (TTT) adapts large language models (LLMs) during inference using only unlabeled test inputs. Existing methods, however, face two major bottlenecks on hard reasoning tasks: (1) \emph{lack of learnable samples}, as self-generated pseudo-labels on difficult questions are often noisy and yield unstable rewards; and (2) \emph{inefficient exploration}, as performance gains depend on repeatedly sampling many rollouts without explicit diagnosis of why previous attempts fail. We propose \textbf{TTSR} (\textbf{T}est-\textbf{T}ime \textbf{S}elf-\textbf{R}eflection), a self-evolving framework based on a \emph{reflect-then-synthesize} paradigm. A single pretrained model alternates between a \textit{Student} role and a \textit{Teacher} role: the Student solves test questions and updates, while the Teacher analyzes failed trajectories and synthesizes targeted variant questions closer to the Student's capability frontier. TTSR further maintains a cross-iteration \textit{weakness memory} and compiles persistent weaknesses into a lightweight \textit{strategy note} prepended to subsequent Student inputs, so diagnostic knowledge can guide exploration and gradually fade as weaknesses are resolved. Experiments on challenging mathematical reasoning benchmarks show consistent test-time improvements, strong cross-backbone generalization, and transfer to general-domain reasoning tasks.

Haoyang He, Zihua Rong, Yunjia Zhao +3

Beijing University of Posts and Telecommunications · Southwestern University of Finance and Economics · China Unicom Online Information Technology Co., Ltd.

Test-Time Training Test Time Mathematical Reasoning Benchmarks Reasoning Skills Reflections

Jan 28, 2026cs.AI

Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution

Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat execution feedback merely as an external signal for filtering or rewriting trajectories, without internalizing it to improve the underlying reasoning strategy. Inspired by Popper's epistemology of "conjectures and refutations," we argue that intelligence requires real-time evolution of the model's policy through learning from failed attempts. We introduce Policy of Thoughts (PoT), a framework that recasts reasoning as a within-instance online optimization process. PoT first generates diverse candidate solutions via an efficient exploration mechanism, then uses Group Relative Policy Optimization (GRPO) to update a transient LoRA adapter based on execution feedback. This closed-loop design enables dynamic, instance-specific refinement of the model's reasoning priors. Experiments show that PoT dramatically boosts performance: a 4B model achieves 49.71% accuracy on LiveCodeBench, outperforming GPT-4o and DeepSeek-V3 despite being over 50 smaller.

Zhengbo Jiao, Hongyu Xian, Qinglong Wang +5

Zhejiang University · South China Normal University · Shanghai University of Finance and Economics +2

LLM Reasoning Strategies Large Language Model Policy Optimization Thoughts Test-Time Training Long-Horizon Task Planning Feedback

Dec 5, 2025cs.CV

SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training

The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suited for this task, as they are often prohibitively slow, destructive to the original asset's identity, or lack the precision for fine-grained control. To address this, we introduce SplatPainter, a state-aware feedforward model that enables continuous editing of 3D Gaussian assets from user-provided 2D view(s). Our method directly predicts updates to the attributes of a compact, feature-rich Gaussian representation and leverages Test-Time Training to create a state-aware, iterative workflow. The versatility of our approach allows a single architecture to perform diverse tasks, including high-fidelity local detail refinement, local paint-over, and consistent global recoloring, all at interactive speeds, paving the way for fluid and intuitive 3D content authoring.

Yang Zheng, Hao Tan, Kai Zhang +4

Stanford University · Adobe

3D Gaussian 3D Editing 3D Assets Canvas Feed-Forward Test-Time Training

Sep 30, 2025stat.ML

Test time training enhances in-context learning of nonlinear functions

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings remain limited, particularly for nonlinear models. In this paper, we investigate the combination of TTT with in-context learning (ICL), where the model is given a few examples from the target distribution at inference time. We analyze this framework in the setting of single-index models, where the feature vector is drawn from a hidden low-dimensional subspace. For single-layer transformers trained with gradient-based algorithms and adopting TTT, we establish an upper bound on the prediction risk. Our theory reveals that TTT enables the single-layer transformers to adapt to both the feature vector and the link function, which vary across tasks. This creates a sharp contrast with ICL alone, which is theoretically difficult to adapt to shifts in the link function. Moreover, we provide the convergence rate with respect to the data length, showing the predictive error can be driven arbitrarily close to the noise level as the context size and the network width grow.

Kento Kuwataka, Taiji Suzuki

Department of Mathematical Engineering and Information Physics The University of Tokyo Hongo 7-3-1, Bunkyo-ku, Tokyo

In-Context Learning Test-Time Training Transformer Architectures Inference-Time Nonlinearity

Jul 8, 2025cs.CL

PERK: Long-Context Reasoning as Test-Time Learning

Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. In this work, we propose PERK (Parameter Efficient Reasoning over Knowledge), a scalable approach for learning to encode long contexts using gradient updates at test time. Specifically, PERK employs two nested optimization loops in a meta-training phase. The inner loop rapidly encodes contexts into a low-rank adapter (LoRA) that serves as a parameter-efficient memory module for the base model. Concurrently, the outer loop learns to use the updated adapter to accurately recall and reason over relevant information from the encoded long context. Our evaluations on several long-context reasoning tasks show that PERK significantly outperforms the standard long-context finetuning, achieving average absolute performance gains of up to 20% for Qwen-2.5 (0.5B & 7B) on synthetic and real-world long-context reasoning. PERK also maintains its advantages across model scales and families. Compared to specialized long-context LLMs, PERK matches or surpasses their performance. Finally, our analyses show PERK is more robust to reasoning complexity, length extrapolation, and the positions of relevant information in contexts. https://perk-long-context.web.app

Zeming Chen, Angelika Romanou, Gail Weiss +1

EPFL

Efficient Long-Context Inference Long-Context Reasoning LLM Reasoning Strategies Test-Time Training