Test-Time Scaling

Follow this topic Ask about this topic

Latest papers 206

30 papers in the last four weeks, up 58% on the four weeks before. 0.2% of all new papers.

All topics

The Capability Frontier: Benchmarks Miss 82% of Model Performance
Jun 25, 2026Bradley Fowler, Ryan Smith, Daniel Thi Graviet +8LLM Evaluation Language Model Generation Evaluation
1Martian · 3ThoughtWorks · University of Oxford
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
Jun 24, 2026Yutong Yin, Mingyu Jin, Jin Pan +12RL for Language Model Reasoning Test-Time Scaling
1Northwestern University · 2Rutgers University · University of Wisconsin–Madison +7
SPIRAL: Learning to Search and Aggregate
Jun 22, 2026Jubayer Ibn Hamid, Ifdita Hasan Orney, Michael Y. Li +5Reinforcement Learning RL for Language Model Reasoning
Stanford University
TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation
Jun 22, 2026Jianuo Cao, Yuxin Chen, Yuzhen Song +3Humanoid Robot Control Test-Time Scaling
Nanjing University · University of California, Berkeley · Southern University of Science and Technology
Depth-Entropy Guided Sampling for Training-Free LLM Reasoning
Jun 19, 2026Zibin Meng, Peng Xie, Kani ChenLLM Inference Test-Time Scaling
1The Hong Kong University of Science and Technology
REVES: REvision and VErification--Augmented Training for Test-Time Scaling
Jun 17, 2026Yuanxin Liu, Ruida Zhou, Xinyan Zhao +6LLM Self-Correction LLM Answer Verification
Northwestern University · Amazon AGI · Qualcomm AI Research +1
DREAM-Chunk: Reactive Action Chunking with Latent World Model
Jun 17, 2026Wenxi Chen, Kaidi Zhang, Chi Lin +6Test-Time Scaling Robotic Manipulation
Purdue University · Stanford University
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Jun 16, 2026Jian Yang, Shawn Guo, Wei Zhang +16Efficient Transformer Inference Test-Time Scaling
1Beihang University · 2IQuest Research · 4Renming University of China +1
Recursive Scaling in Masked Diffusion Models
Jun 16, 2026Alba Carballo-Castro, Julianna Piskorz, Paulius Rauba +2Masked Diffusion Models Diffusion Model Sampling
LTS4, EPFL, Lausanne, Switzerland · University of Cambridge, Cambridge, UK.
Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search
Jun 15, 2026Sidhaarth Murali, João Coelho, Jingjie Ning +3Agentic Search Test-Time Scaling
Carnegie Mellon University, United States · Instituto Superior Técnico and INESC-ID, University of Lisbon, Portugal · NOVA LINCS, NOVA School of Science and Technology, Portugal
Temporal Backtracking Search for Test-time Generative Video Reasoning
Jun 11, 2026Sejoon Jun, Zheng Ding, Huangyuan Su +2Inference-Time Search Test-Time Scaling
Northeastern University · Independent Researcher · Harvard & Kempner +1
MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling
Jun 11, 2026Wenbo Chen, Puheng Li, Mengyang Liu +2LLM Inference Efficiency Self-Consistency Decoding
Amazon · Stanford University · University of Pennsylvania
AVIS: Adaptive Test-Time Scaling for Vision-Language Models
Jun 10, 2026Ahmadreza Jeddi, Minh Ngoc Le, Amirhossein Kazerouni +8Test-Time Adaptation of VLMs Efficient VLM Inference
AI Center-Toronto, Samsung Electronics · University of Toronto · Vector Institute +1
KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty
Jun 9, 2026Sanghee Park, Geewook Kim, Kee-Eung KimVLM Evaluation Mathematical Reasoning Benchmarks
NAVER Cloud AI · KAIST AI
More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs
Jun 7, 2026Marina Igitkhanian, Erik ArakelyanLLM Self-Correction Test-Time Scaling
American University of Armenia · NVIDIA
Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning
Jun 6, 2026Cong Wan, Ying He, Zhongzhan Huang +1Test-Time Scaling Multimodal Reasoning
Sun Yat-sen University
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
Jun 5, 2026Vladislav Smirnov, Chieu Nguyen, Sergey Senichev +14LLM Evaluation Test-Time Scaling
1MBZUAI · 7Independent Researcher · 2ETH Zürich +4
The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models
Jun 4, 2026Jinyang Zhang, Hongxin Ding, Yue Fang +4LLM Interpretability Test-Time Scaling
School of Computer Science, Peking University · National Engineering Research Center of Software Engineering, Peking University · Key Laboratory of High Confidence Software Technologies, Ministry of Education +2
Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)
Jun 3, 2026Nizar Islah, Istabrak Abbes, Irina Rish +2Test-Time Scaling LLM Routing
1Mila - Quebec AI Institute · 2Université de Montréal · 3Polytechnique Montréal +1
Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers
Jun 3, 2026Yacouba Kaloga, Shashi Kumar, Shakeel A. Sheikh +3Inference-Time Scaling Test-Time Scaling
Idiap Research Institute, Switzerland · EPFL, Switzerland · BUT, Czech Republic
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
Jun 2, 2026Runpeng Dai, Tong Zheng, Rui Liu +2Reinforcement Learning Test-Time Scaling
University of North Carolina at Chapel Hill · University of Maryland, College Park · Washington University in St. Louis
Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
Jun 1, 2026Ting Xu, Xu He, Yupu Lu +4CoT Reasoning Test-Time Scaling
The Chinese University of Hong Kong · Huawei Technologies Ltd · School of Computing and Data Science, The University of Hong Kong
ATLAS: Agentic Test-time Learning-to-Allocate Scaling
Jun 1, 2026Peijia Qin, Qi Cao, Pengtao XieTest-Time Scaling Inference-Time Compute Allocation
University of California, San Diego
FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search
May 30, 2026James Xu Zhao, Hui Chen, Bryan Hooi +1LLM Answer Verification Agentic Search
National University of Singapore
SDR: Set-Distance Rewards for Radiology Report Generation
May 30, 2026Halil Ibrahim Gulluk, Max Van Puyvelde, Wim Van Criekinge +1Radiology Report Generation Test-Time Scaling
Department of Electrical Engineering, Stanford University · Department of Biomedical Data Science, Stanford University School of Medicine · Department of Mathematical Modelling, Statistics & Bioinformatics, Ghent University
Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation
May 29, 2026Sang Truong, Yuheng Tu, Rylan Schaeffer +1Language Model Scaling Laws Test-Time Scaling
1Stanford University · University of California, Los Angeles
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
May 26, 2026Xinglin Wang, Hao Lin, Shaoxiong Feng +9Inference-Time Search Test-Time Scaling
School of Computer Science, Beijing Institute of Technology · Xiaohongshu Inc
Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
May 26, 2026Xiao-Wen Yang, Ziyu Han, Xi-Hua Zhang +4Latent Dynamics Modeling Test-Time Scaling
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Artificial Intelligence, Nanjing University, Nanjing, China · School of Intelligence Science and Technology, Nanjing University, Nanjing, China
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
May 25, 2026Meng Cai, Lars Kulik, Farhana ChoudhurySelf-Consistency Decoding Test-Time Scaling
School of Computing and Information Systems University of Melbourne
Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration
May 24, 2026Moyu Zhang, Yun Chen, Yujun Jin +3Cost-Aware Inference Test-Time Scaling
Alibaba Group Beijing, China

Jun 25, 2026J/K move · Enter open · S save

The Capability Frontier: Benchmarks Miss 82% of Model Performance

Bradley Fowler, Ryan Smith, Daniel Thi Graviet, William Myers+7

1Martian · 3ThoughtWorks · University of Oxford

LLM Evaluation Language Model Generation Evaluation Test-Time Scaling LLM Routing Language Model Ensembles

Open paper AskPDF arXiv

Existing benchmarks typically report accuracy for a single model on a single run. This systematically understates real-world LLM capabilities, particularly under heterogeneous data distributions: (i) different models get different questions correct according to their specializations, and (ii) given a budget, multiple generations can be sampled and selectively retained. To quantify this gap, we introduce the Capability Frontier: a Pareto frontier over a set of models that characterizes the best achievable performance at each cost level under optimal selection across models and generations (i.e., via an oracle). Our construction corrects for two opposing biases: underestimation from single-model evaluation and overestimation from taking maxima over noisy samples. We study 21 LLMs across 16 widely used benchmarks spanning coding, reasoning, medicine, factuality, instruction following, and agentic tasks, comparing Capability Frontier performance at matched cost to each benchmark's top-performing model. Correcting for single-model evaluation yields a 54% error rate reduction; additionally correcting for single runs yields an 82% improvement, with SOTA accuracy matched at 85% cost reduction. Complementing these empirical results, we use controlled probabilistic simulations to show that higher query topic entropy produces a near-monotonic increase in the performance gap between oracle routing and the best single model. Our findings suggest collective LLM capabilities are substantially underestimated, with implications for evaluation and deployment in data-heterogeneous, multi-domain settings.