Imagen de Portada

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Snell, Charlie, Lee, Jaehoon, Xu, Kelvin, Kumar, Aviral
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Scaling Test-Time Compute Without Verification or RL is Suboptimal
por: Setlur, Amrith, et al.
Publicado: (2025)

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
por: Setlur, Amrith, et al.
Publicado: (2025)

Test-Time Scaling Makes Overtraining Compute-Optimal
por: Roberts, Nicholas, et al.
Publicado: (2026)

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
por: Monjur, Ocean, et al.
Publicado: (2026)

RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
por: Setlur, Amrith, et al.
Publicado: (2024)

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
por: Setlur, Amrith, et al.
Publicado: (2024)

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
por: Zhao, James Xu, et al.
Publicado: (2025)

Scaling Test-Time Compute for Agentic Coding
por: Kim, Joongwon, et al.
Publicado: (2026)

Test-Time Scaling with Reflective Generative Model
por: Wang, Zixiao, et al.
Publicado: (2025)

J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
por: Chan, Chi-Min, et al.
Publicado: (2025)

Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
por: Zhou, Yilun, et al.
Publicado: (2025)

Resolving Discrepancies in Compute-Optimal Scaling of Language Models
por: Porian, Tomer, et al.
Publicado: (2024)

Predicting Emergent Capabilities by Finetuning
por: Snell, Charlie, et al.
Publicado: (2024)

Provable Scaling Laws for the Test-Time Compute of Large Language Models
por: Chen, Yanxi, et al.
Publicado: (2024)

Atom of Thoughts for Markov LLM Test-Time Scaling
por: Teng, Fengwei, et al.
Publicado: (2025)

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
por: Qu, Yuxiao, et al.
Publicado: (2025)

Value-Based Deep RL Scales Predictably
por: Rybkin, Oleh, et al.
Publicado: (2025)

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
por: MiniMax, et al.
Publicado: (2025)

HEART: Emotionally-Driven Test-Time Scaling of Language Models
por: Pinto, Gabriela, et al.
Publicado: (2025)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
por: Geiping, Jonas, et al.
Publicado: (2025)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
por: Wang, Jian, et al.
Publicado: (2025)

Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving
por: AbdElhameed, Marwan, et al.
Publicado: (2024)

MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
por: Liu, Qin, et al.
Publicado: (2025)

Kinetics: Rethinking Test-Time Scaling Laws
por: Sadhukhan, Ranajoy, et al.
Publicado: (2025)

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance
por: Chen, Tianlang, et al.
Publicado: (2025)

Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
por: Samadi, Mehrzad, et al.
Publicado: (2025)

Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation
por: Chen, Peter Baile, et al.
Publicado: (2025)

Strategic Scaling of Test-Time Compute: A Bandit Learning Approach
por: Zuo, Bowen, et al.
Publicado: (2025)

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
por: Zeng, Zhiyuan, et al.
Publicado: (2025)

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
por: Liu, Yexiang, et al.
Publicado: (2025)

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
por: Ding, Dujian, et al.
Publicado: (2025)

MarkovScale: Towards Optimal Sequential Scaling at Inference Time
por: Wang, Youkang, et al.
Publicado: (2026)

Parallel Test-Time Scaling for Latent Reasoning Models
por: You, Runyang, et al.
Publicado: (2025)

More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
por: Xiong, Weimin, et al.
Publicado: (2025)

Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
por: Bsharat, Sondos Mahmoud, et al.
Publicado: (2025)

Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
por: Karlekar, Sweta, et al.
Publicado: (2026)

Are More Tokens Rational? Inference-Time Scaling in Language Models as Adaptive Resource Rationality
por: Hu, Zhimin, et al.
Publicado: (2026)

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
por: Lab, Mind, et al.
Publicado: (2026)

Compute Optimal Scaling of Skills: Knowledge vs Reasoning
por: Roberts, Nicholas, et al.
Publicado: (2025)

State Tuning: State-based Test-Time Scaling on RWKV-7
por: Xiao, Liu, et al.
Publicado: (2025)