Test-Time Optimization

Follow this topic Ask about this topic

Test-time optimization studies how to improve a pretrained model's answer or behavior using information available for the current input, rather than relying only on training-time changes. Approaches include sampling and verifying multiple candidates, gradient or zeroth-order refinement of latents and outputs, constraint-based optimization, and online updates to model parameters. These methods are used in reasoning and code generation as well as 3D vision, image generation, robotics, and scientific design, where feedback may come from tests, physical constraints, or the input itself. A central challenge is getting reliable gains within a limited compute budget: weak verifiers can reward the wrong result, and optimizing for a metric may not improve real-world quality.

Latest papers

38 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Can machines reason non-verbally?
Oct 9, 2026Shaheer U. Saeed, Zion Tse, Gregory Slabaugh +2Visual Reasoning Test-Time Optimization
Digital Environment Research Institute, Queen Mary University of London · Centre for Bioengineering, Queen Mary University of London · UCL Hawkes Institute, University College London
Improving Predicted MOS Scores, Not Perceived Quality: Multi-Predictor Test-Time Optimization of Enhanced Speech
Sep 30, 2026Tsubasa Ochiai, Marc Delcroix, Nahomi Kusunoki +5Reward Hacking Test-Time Optimization
NTT, Inc., Japan · Waseda University, Japan
Budget Boundary Effects in Test-Time Mathematical Reasoning
Sep 30, 2026Guilin Zhang, Ziqi Tan, Wulan Guo +5Mathematical Reasoning Benchmarks Test-Time Optimization
Yantong AI
VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization
Sep 18, 2026Yibin Zhao, Yihan Pan, Yangwen Li +23D Gaussian Splatting 3D Reconstruction
East China University of Science and Technology Shanghai, China · Shanghai Open University Shanghai, China
Test-Time Scaling for Safe Text-Guided Image Generation via Intermediate Clean Estimates
Aug 4, 2026Jinya Sakurai, Shueicheng Yan, Xun XuTest-Time Optimization T2I Generation
1Nanyang Technological University · 2National University of Singapore · Institute of Advanced Intelligence and Computing (IAIC), A*STAR +1
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Aug 3, 2026Zhaoxin Yu, Qi Shen, Hengli Li +4Test-Time Optimization LLM Interpretability
NLCo Lab, Beijing Institute for General Artificial Intelligence · School of Artificial Intelligence, Beijing University of Posts and Telecommunications · School of Artificial Intelligence for Science, Peking University
Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization
Jul 13, 2026Tian-Shuo Liu, Shiyuan Zhang, Zijie Geng +5Test-Time Optimization Autoformalization
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Polixir Technologies, Nanjing, China · University of Science and Technology of China, Hefei, China
Variational Test-time Optimization for Diffusion Synchronization
Jun 14, 2026Hyunsoo Lee, Farrin Marouf Sofian, Kushagra Pandey +1Inference-Time Optimization Test-Time Optimization
Seoul National University · University of California, Irvine
Test-Time Trajectory Optimization for Autonomous Driving
Jun 5, 2026Yihong Xu, Eloi Zablocki, Yuan Yin +4Trajectory Optimization Trajectory Generation
valeo.ai, Paris, France · Sorbonne Université, CNRS, ISIR, F-75005 Paris, France
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
Jun 3, 2026Peilong Zhou, Zhirong Chen, Cangyuan Li +4RL for Language Models Test-Time Optimization
1SKLP, Institute of Computing Technology, Chinese Academy of Sciences · University of the Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences
Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
May 28, 2026Alaa Khamis, Alaa MaaloufLLM Inference Efficiency Fine-Tuning
Department of Computer Science University of Haifa
RW-TTT: Batched Serving for Request-Owned Test-Time Training State
May 27, 2026Jian Yang, Zhizhuo Kou, Yao Tian +4LLM Serving Test-Time Optimization
1The Hong Kong University of Science and Technology · 2The Chinese University of Hong Kong · 3National University of Singapore
MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
May 25, 2026Linhao Luo, Thuy-Trang Vu, Van-Anh Nguyen +3LLM Alignment Inference-Time Optimization
Monash University · Defence Science and Technology Group, Australia
Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference
May 24, 2026Agata Żywot, Iason Skylitsis, Thijmen Nijdam +4Diffusion Model Guidance Test-Time Optimization
University of Amsterdam, Netherlands
EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
May 15, 2026Guohao Chen, Shuaicheng Niu, Geng Li +4Efficient Neural Network Inference Test-Time Adaptation
Nanyang Technological University · Tulane University
CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
May 15, 2026Fangzhou Lin, Shuo Xing, Peiran Li +6LLM Reasoning Pairwise Comparison
Texas A&M University · Georgia Institute of Technology · Tohoku University +1
Sound Sparks Motion: Audio and Text Tuning for Video Editing
May 14, 2026AmirHossein Naghi Razlighi, Aryan Mikaeili, Ali Mahdavi-Amiri +2Audio-Video Generation Inference-Time Optimization
University of Cyprus, Cyprus · Simon Fraser University, Canada · Tel Aviv University, Israel +1
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation
May 14, 2026Shang Zhou, Wenhao Chai, Kaiyuan Liu +3Pairwise Comparison Test-Time Optimization
1UC San Diego · 2Princeton University · University of Washington +1
Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control
May 14, 2026Nhat Le, Daochang Liu, Anh Nguyen +1Text-to-Motion Generation Test-Time Optimization
The University of Western Australia, Crawley WA 6009, Australia · The University of Liverpool, Liverpool L69 3DR, United Kingdom
Query-Conditioned Test-Time Self-Training for Large Language Models
May 13, 2026Chaehee Song, Minseok Seo, Yeeun Seong +2Test-Time Adaptation Test-Time Optimization
School of Electrical Engineering, KAIST · 2Graduate School of Green Growth and Sustainability, KAIST
Test-Time Speculation
May 10, 2026Avinash Kumar, Sujay Sanghavi, Poulami DasTest-Time Adaptation Test-Time Optimization
The University of Texas at Austin
Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching
May 9, 2026Shan Jiang, Zijian Yi, Chenguang ZhuLLM Inference Efficiency Test-Time Optimization
The University of Texas at Austin
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
May 8, 2026Tong Zheng, Haolin Liu, Chengsong Huang +10LLM Inference Efficiency Automated Algorithm Discovery
UMD · UVA · WUSTL +3
PaT: Planning-after-Trial for Efficient Test-Time Code Generation
May 8, 2026Youngsik Yoon, Sungjae Lee, Seockbean Song +3Test-Time Optimization Execution-Guided Code Generation
Department of Computer Science and Engineering, POSTECH, South Korea · Graduate School of Artificial Intelligence, POSTECH, South Korea · Microsoft Research Asia, Beijing, China
Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs
May 4, 2026Xin Zhang, Qiqi Tao, Jiawei Du +2Inference-Time Optimization Test-Time Optimization
Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore · Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore · Singapore University of Technology and Design +1
Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence
May 2, 2026Panagiotis P. Filntisis, George Retsinas, Radek Daněček +3Test-Time Optimization 3D Reconstruction
Institute of Robotics, Athena Research Center, 15125 Maroussi, Greece · HERON – Hellenic Robotics Center of Excellence, Athens, Greece · School of ECE, NTUA, Greece +3
Compute Aligned Training: Optimizing for Test Time Inference
Apr 27, 2026Adam Ousherovitch, Ambuj TewariTest-Time Optimization Inference-Time Scaling
Department of Statistics University of Michigan
Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations
Apr 22, 2026Bowen Zuo, Dongruo Zhou, Yinglun ZhuEfficient Inference Test-Time Optimization
University of California, Riverside · 2Indiana University Bloomington
Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees
Apr 22, 2026Xueyan Li, Johannes Zenn, Ekaterina Fadeeva +3Language Model Decoding Inference-Time Search
Max Planck Institute for Intelligent Systems · ETH Zurich · AI Center Tübingen +3
TEMPO: Scaling Test-time Training for Large Reasoning Models
Apr 21, 2026Qingyang Zhang, Xinke Kong, Haitao Wu +7Reinforcement Learning Inference-Time Optimization
Tianjin University · Tongyi Lab, Alibaba Group · The Chinese University of Hong Kong +1

Oct 9, 2026J/K move · Enter open · S save

Can machines reason non-verbally?

Shaheer U. Saeed, Zion Tse, Gregory Slabaugh, Daniel C. Alexander+1

Digital Environment Research Institute, Queen Mary University of London · Centre for Bioengineering, Queen Mary University of London · UCL Hawkes Institute, University College London

Visual Reasoning Test-Time Optimization

Open paper AskPDF arXiv

Modern machines can solve equations, follow logic and reason through language, yet they still struggle with problems that require visual non-verbal reasoning. This is evident even in advanced systems such as DeepSeek, ChatGPT and Gemini, which remain limited on visual tasks such as completing abstract patterns or delineating ambiguous regions-of-interest. Unlike explicit intermediate steps in verbal reasoning which can be verified through logic or automated tests, visual reasoning involves implicit intermediate steps with no clear methods for verification. Non-verbal reasoning is therefore challenging to model and, as a result, remains a fundamental limitation of current machine intelligence. Here we introduce GenVerOpt, a general framework that unifies generation, verification and optimisation into a reasoning pipeline for machines. By generating candidate solutions, verifying their correctness, and iteratively refining them, GenVerOpt enables per-sample optimisation rather than relying solely on dataset-level trends captured during model training. This process mirrors human problem-solving where multiple possibilities are imagined, evaluated, and refined until a correct solution emerges. Across diverse domains, GenVerOpt demonstrates capabilities beyond existing systems: it surpasses humans on abstract IQ puzzles, matches clinicians in prostate cancer segmentation, exceeds experts in liver vessel reconstruction and outperforms state-of-the-art approaches in tumour boundary alignment. These results show that machine reasoning can extend beyond language, establishing visual non-verbal reasoning as a foundation for more flexible and generalisable intelligence.