A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
cs.LG
Submitted: 2026-09-01
Updated: 2026-09-01
Comments: accepted by Machine Intelligence Research
DOI: 10.1007/s11633-026-1694-1
Code: https://github.com/mr-eggplant/awesome_test_time_intelligence
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- CTA: Cross-Task Alignment for Better Test Time Training
- ATLAS: Learning to Optimally Memorize the Context at Test Time
- It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Interactive Test-Time Adaptation with Reliable Spatial-Temporal Voxels for Multi-Modal Segmentation
- Test-Time Adaptation for LLM Agents via Environment Interaction
- EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
- Open-World Pose Transfer via Sequential Test-Time Adaption
- TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
- Learning to Self-Verify Makes Language Models Better Reasoners
- TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
- Test Time Learning for Time Series Forecasting
- Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning
- Training Verifiers to Solve Math Word Problems
- BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis
- Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion
- RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model
- Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning
- Adaptive Computation Time for Recurrent Neural Networks
- Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks