Inference-Time Scaling

Follow this topic Ask about this topic

Inference-time scaling asks how models can use additional computation after training to solve harder problems, improve generation, or act more reliably. Common approaches include sampling and self-consistency, search and backtracking, verifier-guided selection, recurrent computation, and adaptive allocation across tasks or agents; they are tested on settings such as math, code, theorem proving, scientific discovery, and embodied planning. Results often improve with more compute, but gains depend on the task, budget, and quality of selection signals, and can come with substantial latency and resource costs. A central tension is deciding when extra computation helps: correlated errors, weak verifiers, or longer erroneous trajectories can make scaling ineffective or even harmful, so evaluations increasingly compare methods at matched budgets.

Latest papers

115 papers27 papers in the last four weeks, up 170% on the four weeks before. 0.2% of all new papers.

Recursive Agent Optimization
May 7, 2026Apurva Gandhi, Satyaki Chakraborty, Xiangjun Wang +2Agentic RL Inference-Time Scaling
Carnegie Mellon University · Amazon AGI Labs
Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling
May 2, 2026Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle +2Self-Consistency Decoding Cost-Aware Inference
University of Göttingen, Germany
Compute Aligned Training: Optimizing for Test Time Inference
Apr 27, 2026Adam Ousherovitch, Ambuj TewariTest-Time Optimization Inference-Time Scaling
Department of Statistics University of Michigan
Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
Apr 23, 2026Hao-Yuan ChenInference-Time Scaling Process Supervision
Mindify AI Research · University of London · Senate House, Malet Street, London WC1E 7HU, United Kingdom
Evaluation-driven Scaling for Scientific Discovery
Apr 21, 2026Haotian Ye, Haowei Lin, Jingyi Tang +22Large Language Model-Guided Optimization Inference-Time Scaling
Wizard Intelligence Learning Lab, Stanford University · Peking University, Tsinghua University
Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling
Apr 19, 2026Zizhang Luo, Yuhao Luo, Youwei Xiao +3LLM Inference Efficiency Multi-Agent LLM Systems
Peking University Beijing, China
FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time
Apr 17, 2026Montgomery Bohde, Hongxuan Liu, Mrunali Manjrekar +4Inference-Time Scaling Molecular Generation
Massachusetts Institute of Technology, Cambridge, MA, United States · Texas A&M University, College Station, TX, United States
Generalization in LLM Problem Solving: The Case of the Shortest Path
Apr 16, 2026Yao Tong, Jiayuan Ye, Anastasia Borovykh +1Inference-Time Scaling Language Model Generalization
National University of Singapore · Capital Fund Management · Google Research
Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents
Apr 13, 2026S. Aaron McClendon, Jorge Gallego-Feliciano, Stavros Zervoudakis +1Tool-Using Language Agents LLM Agent Workflow Optimization
Aimpoint Digital Labs, Atlanta, GA, USA · New York University, New York, NY, USA
Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models
Apr 7, 2026Xiangming Gu, Soham De, Larisa Markeeva +2Parallel Reasoning in Language Models Large Reasoning Models
Google DeepMind · National University of Singapore
Universal YOCO for Efficient Depth Scaling
Apr 1, 2026Yutao Sun, Li Dong, Tianzhu Ye +3Efficient Language Model Inference Inference-Time Scaling
Microsoft Research · Tsinghua University
Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute Scaling
Apr 1, 2026Hongbeen Kim, Juhyun Lee, Sanghyeon Lee +2Monte Carlo Tree Search LLM Inference Acceleration
School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea.
Video Models Reason Early: Exploiting Plan Commitment for Maze Solving
Mar 31, 2026Kaleb Newman, Tyler Zhu, Olga RussakovskyVideo Diffusion Models Video Reasoning
Princeton University
Tiny Inference-Time Scaling with Latent Verifiers
Mar 23, 2026Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi +3Inference-Time Scaling Diffusion Models
University of Modena and Reggio Emilia, Italy · University of Pisa, Italy
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
Mar 15, 2026Zengqun Zhao, Ziquan Liu, Yu Cao +5Video Diffusion Models Inference-Time Scaling
Queen Mary University of London · Huawei R&D UK · Imperial College London
Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs
Mar 13, 2026Guchan Li, Rui Tian, Hongning WangAutomated Theorem Proving Efficient Language Model Reasoning
Department of Computer Science and Technology, Tsinghua University, Beijing, China.
Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
Mar 11, 2026Linus Folkerts, Will Payne, Simon Inman +11LLMs for Cybersecurity AI Agent Evaluation
AI Security Institute, United Kingdom.
Improving reasoning at inference time via uncertainty minimisation
Mar 7, 2026Nicolas Legrand, Kenneth Enevoldsen, Márton Kardos +1Efficient Language Model Reasoning Inference-Time Scaling
Center for Humanities Computing Aarhus University, Denmark
Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation
Feb 22, 2026Xiangyu Liu, Di Wang, Zhe Feng +1Repeated Games Multi-Agent Negotiation
Google Research · University of Maryland, College Park
Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness
Feb 20, 2026Yegor Denisov-Blanch, Joshua Kazdan, Jessica Chudnovsky +4Correlated Errors in Language Models Inference-Time Scaling
Stanford Computer Science · Stanford Statistics · Stanford University +1
Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
Feb 13, 2026Wei-Lin Chen, Liqian Peng, Tian Tan +5LLM Inference Efficiency Inference-Time Scaling
University of Virginia · Google
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
Nov 24, 2025Long Lian, Sida Wang, Felix Juefei-Xu +7Parallel Reasoning in Language Models RL for Language Model Reasoning
Meta Superintelligence Labs (MSL), Menlo Park, CA, United States · UC Berkeley, Berkeley, CA, United States · UCSF, San Francisco, CA, United States
Optimal Self-Consistency for Efficient Reasoning with Large Language Models
Nov 15, 2025Austin Feng, Marius Alonso, Ambroise Odonnat +2Self-Consistency Decoding Inference-Time Scaling
1Yale University, New Haven, CT, USA · 2Noah’s Ark Lab, Paris, France · 3Inria, Rennes, France +1
Reasoning in machine vision by learning fast and slow thinking
Jun 27, 2025Shaheer U. Saeed, Yipei Wang, Veeru Kasivisvanathan +4Visual Reasoning Dual-Process Reasoning
Centre for Bioengineering, Queen Mary University of London, London, UK · Digital Environment Research Institute, Queen Mary University of London, London, UK · School of Engineering and Materials Science, Queen Mary University of London, London, UK +6
Scaling Evaluation-time Compute with Reasoning Models as Evaluators
Mar 25, 2025Seungone Kim, Ian Wu, Jinu Lee +8LLM Evaluation Language Model Generation Evaluation
CMU · UIUC2 · KAIST AI3 +3

May 7, 2026J/K move · Enter open · S save

Recursive Agent Optimization

Apurva Gandhi, Satyaki Chakraborty, Xiangjun Wang, Aviral Kumar+1

Carnegie Mellon University · Amazon AGI Labs

Agentic RL Inference-Time Scaling LLM Agent Training

Open paper AskPDF arXiv

We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new instantiations of themselves recursively. Recursive agents implement an inference-time scaling algorithm that naturally allows agents to scale to longer contexts and generalize to more difficult problems via divide-and-conquer. RAO provides a method to train models to best take advantage of such recursive inference, teaching agents when and how to delegate and communicate. We find that recursive agents trained in this way enjoy better training efficiency, can scale to tasks that go beyond the model's context window, generalize to tasks much harder than the ones the agent was trained on, and can enjoy reduced wall-clock time compared to single-agent systems.