The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifie…

This paper proposes a source-free continual test-time adaptation methodology using a controlled teacher adaptation and class prototype estimation.

This paper introduces Test-Time Harness Evolution (TTHE), a method for optimizing LLM agent harnesses during evaluation using execution traces, without requiring gold labels or training.

The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, lead…

This paper proposes a context-aware AI framework for generating telecom test scripts that adapt to fine-grained changes in the system using a delta engine and a knowledge graph.

TIMEGATE introduces a resource-aware policy layer that manages continual ML adaptation by dynamically budgeting time and evaluation resources, achieving significant compute and energy savings without…

The paper introduces TopoTTA, a framework that uses persistent homology for topological data analysis to enhance the quality of anomaly segmentation in deep models, leading to an average 15% F1 improv…

This paper introduces ElasticTTT, a framework to preserve the generative prior in Test-Time Tuning (TTT) of pretrained diffusion models for video editing, preventing Prior Collapse.

The paper introduces a sample-wise targeted adversarial attack that successfully misclassifies only specific, triggered inputs during test-time adaptation while maintaining the overall label distribut…

This paper identifies modality-order sensitivity as a failure in vision-language models and introduces a test-time training method to mitigate it, resulting in improved performance.

This paper introduces Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scales visuomotor context to 8K timesteps, enabling new capabilities like one-shot imitation a…

The paper introduces Gradient-based Behavior Vector-Parameter Delta (GBV-PD), an approach for evolution-aware regression test prioritization in ML-enabled systems using gradient-based behavior vectors…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

The paper introduces a framework to quantitatively measure evolving agent behaviors (traits) by analyzing changes in their configuration text files, achieving high accuracy in classifying behavioral s…

This paper evaluates the performance of large language models on popular benchmarks and finds that only a small percentage of the performant implementations are significantly faster than canonical sol…

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…

This paper tests the assumption that evaluation is easier than generation in LLM-as-a-Judge and self-evaluation pipelines using a controlled in-context QA setting and reveals that evaluation attends t…

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…