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

• URL: http://arxiv.org/abs/2609.01679v1
• Date: Tue, 01 Sep 2026 11:41:39 GMT
• Title: A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
• Abstract summary: We present feedback-driven Test-Time Intelligence (TTI) as a unified perspective for understanding such deployment-time improvement.<n>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.<n>Our goal is to provide a coherent foundation and research roadmap for the study of self-improving AI systems at test time.
• Score: 72.19201465132619
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Test-Time Learning with an Evolving Library [76.87197412229318]
  EvoLib is a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge.<n>Instead of adapting model parameters, our approach maintains a shared library of knowledge abstractions.
  arXiv  Detail & Related papers  (2026-05-14T07:18:12Z)
• Decoding AI Tutor Effects for Educational Measurement: Temporal, Multi-Outcome, and Behavior-Cognitive Analysis [0.3342165620612816]
  We propose an AI agent prototype framework for exploring AI-assisted learning with temporal interaction patterns, multiple outcomes analysis, and behavioral-cognitive learner profiling.<n>An AI tutor agent has been developed to provide various feedback forms to learners, including hints, explanations, examples, and code.<n>A neural policy model and simulation framework are used to produce artificial student-AI tutor interaction records, which include response time, attempts, hint requests, correctness, quiz results, improvement, satisfaction, and trust.<n>The results showed that early interaction patterns were predictive of later performance and trust, that student behavior changed over time with AI-based tutoring, and
  arXiv  Detail & Related papers  (2026-03-22T00:43:17Z)
• TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement [7.122068644799895]
  Test-time Training enables model adaptation using only test questions.<n>We propose textbfTTSR, a self-reflective test-time self-evolving training framework.
  arXiv  Detail & Related papers  (2026-02-06T18:55:40Z)
• Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning [15.567266973412815]
  We extend predictive models to automatically detect socially shared regulation of learning behaviors using embedding-based approaches.<n>We leverage large language models (LLMs) as summarization tools to generate task-aware representations of student dialogue aligned with system logs.<n>Results show that text-only embeddings often achieve stronger performance in detecting SSRL behaviors related to enactment or group dynamics.
  arXiv  Detail & Related papers  (2026-01-08T00:30:46Z)
• A Survey on Generative Recommendation: Data, Model, and Tasks [55.36322811257545]
  generative recommendation reconceptualizes recommendation as a generation task rather than discriminative scoring.<n>This survey provides a comprehensive examination through a unified tripartite framework spanning data, model, and task dimensions.<n>We identify five key advantages: world knowledge integration, natural language understanding, reasoning capabilities, scaling laws, and creative generation.
  arXiv  Detail & Related papers  (2025-10-31T04:02:58Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [57.19302613163439]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models [3.0495235326282186]
  In deep learning, maintaining robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time.
  arXiv  Detail & Related papers  (2024-05-23T18:27:07Z)
• Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspective [68.20531518525273]
  We take a closer look into existing self-supervised methods of speech from an information-theoretic perspective. We use linear probes to estimate the mutual information between the target information and learned representations. We explore the potential of evaluating representations in a self-supervised fashion, where we estimate the mutual information between different parts of the data without using any labels.
  arXiv  Detail & Related papers  (2024-01-16T21:13:22Z)
• Accelerating exploration and representation learning with offline pre-training [52.6912479800592]
  We show that exploration and representation learning can be improved by separately learning two different models from a single offline dataset. We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward can significantly improve the sample efficiency on the challenging NetHack benchmark.
  arXiv  Detail & Related papers  (2023-03-31T18:03:30Z)
• Testing Deep Learning Models: A First Comparative Study of Multiple Testing Techniques [15.695048480513536]
  Vision-based systems (VBS) are used in autonomous driving, robotic surgery, critical infrastructure surveillance, air and maritime traffic control, etc. Deep Learning (DL) has revolutionized the capabilities of vision-based systems (VBS) in critical applications such as autonomous driving, robotic surgery, critical infrastructure surveillance, air and maritime traffic control, etc.
  arXiv  Detail & Related papers  (2022-02-24T15:05:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.