Cover Image

IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Zhoujun, Xie, Yutao, Qu, Yuxiao, Setlur, Amrith, Hao, Shibo, Pimpalkhute, Varad, Liang, Tongtong, Yao, Feng, Liu, Zhengzhong, Xing, Eric, Smith, Virginia, Salakhutdinov, Ruslan, Hu, Zhiting, Killian, Taylor, Kumar, Aviral
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
by: Qu, Yuxiao, et al.
Published: (2026)

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
by: Wu, Ian, et al.
Published: (2026)

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

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
by: Qu, Yuxiao, et al.
Published: (2025)

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

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

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
by: Deng, Mingkai, et al.
Published: (2026)

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

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
by: LM-Provers, et al.
Published: (2026)

Multi-Agent Computer Use
by: Koh, Jing Yu, et al.
Published: (2026)

SoftQE: Learned Representations of Queries Expanded by LLMs
by: Pimpalkhute, Varad, et al.
Published: (2024)

On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
by: Thaker, Pratiksha, et al.
Published: (2023)

Compute-Optimal Scaling for Value-Based Deep RL
by: Fu, Preston, et al.
Published: (2025)

Lower Bounds for Public-Private Learning under Distribution Shift
by: Setlur, Amrith, et al.
Published: (2025)

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
by: Setlur, Amrith, et al.
Published: (2026)

Response to Promises and Pitfalls of Deep Kernel Learning
by: Wilson, Andrew Gordon, et al.
Published: (2025)

Exact Unlearning of Finetuning Data via Model Merging at Scale
by: Kuo, Kevin, et al.
Published: (2025)

What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?
by: Kang, Katie, et al.
Published: (2024)

InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning
by: Yang, Matthew Y. R., et al.
Published: (2026)

Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
by: Dalal, Murtaza, et al.
Published: (2024)

Deep Neural Networks Tend To Extrapolate Predictably
by: Kang, Katie, et al.
Published: (2023)

floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
by: Agrawalla, Bhavya, et al.
Published: (2025)

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

K2-Think: A Parameter-Efficient Reasoning System
by: Cheng, Zhoujun, et al.
Published: (2025)

Recursive Introspection: Teaching Language Model Agents How to Self-Improve
by: Qu, Yuxiao, et al.
Published: (2024)

Contrastive Difference Predictive Coding
by: Zheng, Chongyi, et al.
Published: (2023)

Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation
by: Duan, Xintong, et al.
Published: (2025)

Computing the Volume of Polytropes
by: Hong-Minh, Killian, et al.
Published: (2025)

Act2See: Emergent Active Visual Perception for Video Reasoning
by: Ma, Martin Q., et al.
Published: (2026)

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
by: Zheng, Chongyi, et al.
Published: (2023)

Concise Reasoning in the Lens of Lagrangian Optimization
by: Gao, Chengqian, et al.
Published: (2025)

The Digital Playbook
Published: (2023)

The Sports Playbook
by: Gordon, Joshua A., et al.
Published: (2022)

'Legends' Teaching and Learning with Technology in Teen Space
by: Virginia Killian Lund
Published: (2024)

Transferable Utility Matching Beyond Logit: Computation and Estimation with General Heterogeneity
by: Galichon, Alfred, et al.
Published: (2025)

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
by: Snell, Charlie, et al.
Published: (2024)

Multitask Learning Can Improve Worst-Group Outcomes
by: Kulkarni, Atharva, et al.
Published: (2023)

CaRT: Teaching LLM Agents to Know When They Know Enough
by: Liu, Grace, et al.
Published: (2025)

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
by: Lai, Hanyu, et al.
Published: (2025)

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
by: Shen, Junhong, et al.
Published: (2025)