"test-time compute" Papers
6 papers found
Conference
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Kanishk Gandhi, Ayush K Chakravarthy, Anikait Singh et al.
COLM 2025paperarXiv:2503.01307
318
citations
Exact Expressive Power of Transformers with Padding
Will Merrill, Ashish Sabharwal
NEURIPS 2025arXiv:2505.18948
7
citations
Interpreting Emergent Planning in Model-Free Reinforcement Learning
Thomas Bush, Stephen Chung, Usman Anwar et al.
ICLR 2025arXiv:1901.03559
125
citations
Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers
Shalev Lifshitz, Sheila A. McIlraith, Yilun Du
COLM 2025paperarXiv:2502.20379
31
citations
Rank1: Test-Time Compute for Reranking in Information Retrieval
Orion Weller, Kathryn Ricci, Eugene Yang et al.
COLM 2025paperarXiv:2502.18418
47
citations
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
Wenkai Yang, Shuming Ma, Yankai Lin et al.
NEURIPS 2025arXiv:2502.18080
103
citations