Test-Time Scaling

Latest papers 205

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

Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling
Oct 13, 2026Cong Hua, Qianqian Xu, Zitai Wang +4LLM Reasoning Test-Time Scaling
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences. · School of Computer Science and Technology, University of Chinese Academy of Sciences. · Beijing Academy of Artificial Intelligence. +1
Input-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners
Oct 13, 2026Haochen Shi, Tianwen Fu, Qianggang Ding +7Inference-Time Search Inference-Time Scaling
Mila – Quebec AI Institute · Université de Montréal · University of Southern California +2
LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers
Oct 13, 2026Zipeng Wang, Anping Xiong, Jing Zhang +17Diffusion-Based Image Generation Diffusion Transformer
Chongqing University of Posts and Telecommunications · China United Network Communications Group Co., Ltd. · University of Electronic Science and Technology of China +1
Fewer Bits, More Tries: Recovering Capability Under Memory Constraints
Oct 11, 2026Tomer Galanti, Josh Susskind, Eran MalachTest-Time Scaling LLM Inference Acceleration
Texas A&M · Apple
Test-Time Compute for Humanoid Behavior Foundation Models
Oct 10, 2026Weiji Xie, Junsong Wu, Zibo Zhou +5Inference-Time Optimization Robot Foundation Models
Institute of Artificial Intelligence (TeleAI), China Telecom · Shanghai Jiaotong University · Zhejiang University +1
Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies
Oct 10, 2026Chen Zhao, Zipeng Ye, Haitao Shen +3Test-Time Scaling Vision-Language-Action Models
Renmin University of China, Beijing 100872, China · Key Laboratory of Data Engineering and KnowledgeEngineering, MOE, China · Meituan, Beijing 100102, China
From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
Oct 7, 2026Xinglin Wang, Zishen Liu, Tong Zheng +9Test-Time Scaling Cost-Aware Inference
Beijing Institute of Technology · Xiaohongshu Inc
CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
Oct 5, 2026Yifan Zhang, Yutong Dai, Viraj Prabhu +3Test-Time Scaling RL for LLM Agents
Salesforce AI Research
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
Oct 4, 2026Seongheon Park, Heecheol Kim, Shulin Tian +5Vision-Language-Action Models Test-Time Scaling
University of Wisconsin–Madison · Microsoft Research Asia–Tokyo · Nanyang Technological University +2
Refinement Buys Intelligibility, Search Buys Identity: What Test-Time Compute Buys in Masked-Diffusion TTS
Oct 2, 2026Nityanand Mathur, Hamees Sayed, Ayush Pratap SinghTTS Synthesis Text-to-Speech
Work done outside of Blackstar Inc. · Work done at Smallest AI.
Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
Oct 1, 2026Azal Ahmad Khan, Keshav Ramji, Tahira Naseem +2Test-Time Adaptation Test-Time Scaling
University of Minnesota · IBM Research AI
Sharpening Tax in Post-Training
Oct 1, 2026Changdae Oh, Qi Zeng, Qi Qi +7Agentic RL Test-Time Scaling
Meta Superintelligence Labs · University of Wisconsin–Madison · Work done at Meta +2
How Much Can Language Models Gain from Test-Time Computation?
Oct 1, 2026Bangji Yang, Jingyuan Li, Jiajun Fan +8LLM Evaluation Test-Time Scaling
University of Illinois at Urbana-Champaign · University of Washington · Tsinghua University
Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves
Sep 30, 2026Sohail, Sarkar, Shakuntala BaichooBenchmark Auditing Test-Time Scaling
Neel · PMCC AI Lab, Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Sep 30, 2026Minki Kang, Ryo Hachiuma, Shaokun Zhang +8Terminal Agents Test-Time Scaling
NVIDIA · KAIST
Towards Better Exploration in Sequential Test-Time Scaling
Sep 30, 2026Joseph Rance, Fabio Pizzati, Juil Sock +4Test-Time Scaling
University of Oxford · MBZUAI · BBC R&D
Taming Speculative Search for Test-Time Scaling in LLM Serving
Sep 30, 2026Jinwoo Jeong, Woohyung Choi, Myeongjae Jeon +1LLM Inference Acceleration LLM Serving
Korea University · Korea University Seoul, Republic of Korea · POSTECH +1
RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent
Sep 30, 2026Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong +3Contrastive Learning LLM Self-Refinement
Huawei Technologies, Co., Ltd.
DeepJEPA: Scaling World Models from Within
Sep 30, 2026Zijian Jin, Yunbei Zhang, Yuanzhe Liu +5World Model Learning World Model-Based Planning
New York University · Tulane University · UIUC +4
Provable Test-Time Scaling for Beam Search in LLM Reasoning
Sep 29, 2026Qijia He, Yu Huang, Yuan Cheng +2Inference-Time Search Test-Time Scaling
The Ohio State University · University of Pennsylvania · National University of Singapore
Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling
Sep 29, 2026Xinyu Li, Mononito Goswami, Hao Liu +5LLM Inference Inference-Time Scaling
Carnegie Mellon University · AWS AI Labs · Washington University in St. Louis +1
OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization
Sep 29, 2026Chenxing Wei, Sichen Liu, Lizhao Liu +6Large Language Model-Guided Optimization Test-Time Scaling
School of Computing and Data Science, The University of Hong Kong · Shenzhen Loop Area Institute · ByteDance +3
Learning via Self-Consistency for Diffusion-based Video Reasoning
Sep 29, 2026Zhenghao Ni, Weimin Qiu, Meng TangVideo Diffusion Models Self-Consistency Decoding
University of Toronto · University of California, Merced
Improving Test-Time Scaling with Adaptive Looped Transformers
Sep 28, 2026Yichen You, Tianyu Fu, Aosong Feng +4Test-Time Scaling Recurrent Transformers
Tsinghua University · Yale University
Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning
Sep 28, 2026Hao-Xuan Ma, Yihao Liu, Yutao Sun +8Test-Time Scaling for VLMs Test-Time Scaling
Qwen Business Unit of Alibaba · School of Artificial Intelligence, Nanjing University · National Key Laboratory for Novel Software Technology, Nanjing University +5
Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning
Sep 27, 2026Ruosong Ye, Caiqi Zhang, Jiahao Li +9Test-Time Scaling Multi-Agent Debate
Rutgers University, New Brunswick · University of Cambridge · Tsinghua University +4
Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?
Sep 27, 2026Yuyang Zhao, Xuan Liu, HaoYang Shang +1Test-Time Scaling Human Behavior Prediction
University of California, San Diego
Planned Test-Time Scaling with Coordinated Reasoning Paths
Sep 23, 2026Xueqing Wu, Langxing Bai, Hritik Bansal +5RL for Language Model Reasoning Test-Time Scaling
University of California, Los Angeles · Amazon
CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
Sep 22, 2026Trang Nguyen, Eulrang Cho, Bingqing Chen +1Continual Learning for LLM Agents Test-Time Scaling
Carnegie Mellon University · Bosch Center for AI
Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training
Sep 22, 2026Jacob Beck, Philip V. Ogren, Ari KobrenInference-Time Search Evolution Strategies
Oracle

Oct 13, 2026J/K move · Enter open · S save

Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling

Cong Hua, Qianqian Xu, Zitai Wang, Zhiyong Yang+3

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences. · School of Computer Science and Technology, University of Chinese Academy of Sciences. · Beijing Academy of Artificial Intelligence.+1

LLM Reasoning Test-Time Scaling Rank Aggregation

Open paper AskPDF arXiv

Sampling-based test-time scaling enhances LLM reasoning by aggregating multiple reasoning paths for the same query. Existing methods use answer frequencies or path confidence to compute candidate scores, which do not explicitly characterize comparisons between competing answers. Inspired by the Condorcet principle in social choice theory, we introduce pairwise confidence comparisons between paths supporting different answers to capture answer-level comparative advantage. We combine this comparative evidence with voting support through a KL-regularized objective. Theoretically, we show that this comparative-advantage is equivalent to the adjustment to the traditional voting logits. In this way, our proposed Pairwise-Guided Logit Adjustment (PGLA) framework allows comparative evidence to compensate for weaker voting support and correct voting-based ranking errors. Experiments on 10 challenging benchmarks including mathematical reasoning, knowledge reasoning, and code generation with 7 models ranging from 1.7B to 32B parameters speak to the effectiveness of this plug-and-play term. Additional evaluations with external reward scores and online sampling further demonstrate its applicability.