Test-Time Scaling

Latest papers 206

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

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
May 22, 2026Zhangyi Hu, Chenhui Liu, Tian Huang +6LLM Self-Refinement Execution-Guided Code Generation
1The Hong Kong University of Science and Technology (Guangzhou) · Institute of Deep Perception Technology, JITRI, Wuxi, China
DeliCIR: Deliberative Test-Time Evolutionary Hierarchical Multi-Agents for Composed Image Retrieval
May 21, 2026Xingtian Pei, Yukun Song, Changwei Wang +4Test-Time Scaling Multimodal Agents
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China · Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, 250013, China; Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, 250014, China · School of Artificial Intelligence, Mohamed bin Zayed University, Abu Dhabi 51133, United Arab Emirates
ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
May 21, 2026Woomin Song, Beomjun Kim, Daewon Choi +4Test-Time Scaling Multi-Agent Systems
1KAIST · 2Amazon AGI · 3Together AI
Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion
May 21, 2026Gang Dai, Yining Huang, Yiming Xia +2Test-Time Scaling Diffusion-Based Image Generation
Guangdong University of Technology · South China University of Technology · Nanyang Technological University
Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
May 20, 2026Benhao Huang, Zhengyang Geng, Zico KolterDynamical Systems Test-Time Scaling
CMU
Code Generation by Differential Test Time Scaling
May 19, 2026Yifeng He, Ethan Wang, Jicheng Wang +2Differential Testing Execution-Guided Code Generation
University of California, Davis · Wuhan University · University of Hong Kong
Probabilistic Tiny Recursive Model
May 19, 2026Amin Sghaier, Ali Parviz, Alexia Jolicoeur-MartineauTest-Time Scaling
Mila – Quebec AI Institute ILLS & ETS Montreal · Independent
GIM: Evaluating models via tasks that integrate multiple cognitive domains
May 18, 2026Rohit Patel, Alexandre Rezende, Steven McClainLLM Evaluation Test-Time Scaling
Meta Superintelligence Labs
SurgLQA: Scalable Long-Horizon Surgical Video Question Answering
May 18, 2026Diandian Guo, Xikai Yang, Ruiyang Li +2Temporal Video Grounding Test-Time Scaling
The Chinese University of Hong Kong
Verifiers in the Loop: Decoding Time Verification for Code Translation
May 17, 2026Tianyang Zhou, Somesh Jha, Mihai Christodorescu +2Code Translation Constrained Decoding
University of Illinois Urbana-Champaign · University of Wisconsin–Madison and Google · Google
CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
May 15, 2026Fangzhou Lin, Shuo Xing, Peiran Li +6Pairwise Comparison Pairwise Preference Evaluation
Texas A&M University · Georgia Institute of Technology · Tohoku University +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
Stateful Reasoning via Insight Replay
May 14, 2026Bin Lei, Caiwen Ding, Jiachen Yang +2Memory-Augmented Language Models CoT Reasoning
University of Minnesota · 2Simular AI
LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
May 13, 2026Qi Cao, Yufan Wang, Peijia Qin +2LLM Inference Test-Time Scaling
University of California, San Diego
Test-Time Hinting for Black-Box Vision-Language Models
May 13, 2026Kaihua Hou, Abhijith Varma Mudunuri, Jiaxing Qiu +3Visual Question Answering VLM Adaptation
UC Berkeley · UCSF · University of Virginia +1
Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
May 11, 2026Yizhu Jiao, Ruixiang Zhang, Richard Bai +3RL for Code Generation Test-Time Scaling
Apple · University of Illinois Urbana-Champaign
What should post-training optimize? A test-time scaling law perspective
May 11, 2026Muheng Li, Jian Qian, Wenlong MouTest-Time Scaling Best-of-N Sampling
Department of Statistical Sciences, University of Toronto† · Department of AI and Data Science, The University of Hong Kong ⋄
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
May 11, 2026George Wu, Nan Jing, Qing Yi +7Multi-Agent LLM Systems RL for Language Model Reasoning
1IQuest Research · 2Beihang University
Simply Stabilizing the Loop via Fully Looped Transformer
May 11, 2026Rao Fu, Zixuan Yang, Jiankun Zhang +4Test-Time Scaling Recurrent Transformers
Hong Kong Baptist University · Jilin University
Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization
May 9, 2026Xingyuan Hua, Sheng Yue, Ju RenRL for Language Model Reasoning Test-Time Scaling
Department of Computer Science and Technology, Tsinghua University, Beijing, China · State Key Laboratory of Internet Architecture, Tsinghua University, Beijing, China · School of Cyber Science and Technology, Sun Yat-sen University Shenzhen Campus, Shenzhen, China
Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures
May 9, 2026Linhai Zhang, Yulan HeReward Modeling Reward Hacking
King’s College London · The Alan Turing Institute
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
BitCal-TTS: Bit-Calibrated Test-Time Scaling for Quantized Reasoning Models
May 7, 2026Sai Babu Patarlapalli, Surya Teja AvvaruLLM Inference 4-Bit Quantization
ZAYA1-8B Technical Report
May 6, 2026Robert Washbourne, Rishi Iyer, Tomas Figliolia +15Mixture-of-Experts Language Models RL for Language Model Reasoning
Zyphra San Francisco, CA
Stream-T1: Test-Time Scaling for Streaming Video Generation
May 6, 2026Yijing Tu, Shaojin Wu, Mengqi Huang +4Streaming Video Generation Test-Time Scaling
University of Science and Technology of China · Independent Researcher
Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference
May 5, 2026Yi LiuLLM Inference Test-Time Scaling
York University
HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
May 4, 2026Jianing Wang, Linsen Guo, Zhengyu Chen +8RL for Language Model Reasoning Test-Time Scaling
Meituan LongCat Team · National Engineering Research Center for Software Engineering, Peking University, Beijing, China
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
Apr 29, 2026Zhimin Lin, Yixin Ji, Jinpeng Li +5Test-Time Scaling LLM Routing
School of Computer Science and Technology, Soochow University · Department of Foundation Model, 2012 Labs, Huawei · 3Harbin Institute of Technology, Shenzhen (HITSZ)
Entropy Centroids as Intrinsic Rewards for Test-Time Scaling
Apr 28, 2026Wenshuo Zhao, Qi Zhu, Xingshan Zeng +4LLM Inference Test-Time Scaling
May · HKUST · ZJU +1
Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scaling
Apr 28, 2026Ardit Krasniqi, Luan Vejsiu, Elira DervishiInference-Time Optimization Process Reward Models
European University of Tirana

May 22, 2026J/K move · Enter open · S save

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test

Zhangyi Hu, Chenhui Liu, Tian Huang, Jindong Li+5

1The Hong Kong University of Science and Technology (Guangzhou) · Institute of Deep Perception Technology, JITRI, Wuxi, China

LLM Self-Refinement Execution-Guided Code Generation Code Generation Test-Time Scaling Automated Test Generation LLM Code Generation

Open paper AskPDF arXiv

Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data.