No article text was recorded for this version.
inference-time compute scaling (test-time compute scaling)
Version 2 of 2819 papers1,102 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs
- Blog: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
- Blog: J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
- Blog: Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
- Blog: Can Test-Time Scaling Improve World Foundation Model?
- Blog: Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
- Blog: Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
- Blog: TEST-TIME SCALING IN DIFFUSION LLMS VIA HIDDEN SEMI-AUTOREGRESSIVE EXPERTS
- Blog: RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering
- Blog: Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG
- Blog: From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
- Blog: Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning Quality
- Blog: Video-T1: Test-time Scaling for Video Generation
- Blog: Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
- Blog: VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
- Blog: Scaling Properties of Diffusion Models For Perceptual Tasks
- Blog: Tree Search for Language Model Agents
- Blog: Can Test-Time Scaling Improve World Foundation Model?
- Blog: Understanding the Role of Training Data in Test-Time Scaling
- Blog: Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving
- Blog: Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond
- Blog: A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law
- Blog: LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
- Blog: s1: Simple test-time scaling
- Blog: From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
- Blog: Learn to Explore In-Context via Reinforcement Learning
- Blog: Training-Free Multi-Step Audio Source Separation
- Blog: A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges
- Blog: Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
- Blog: DeepSeek vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?
- Blog: MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
- Blog: VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
- Blog: MedOS: AI-XR-Cobot World Model for Clinical Perception and Action
- Blog: LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
- Blog: A Survey of Reinforcement Learning for Large Reasoning Models
- Blog: Generative AI Act II: Test Time Scaling Drives Cognition Engineering
- Blog: Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
- Blog: Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
- Blog: SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?
- Blog: International AI Safety Report
- Blog: LLM Post-Training: A Deep Dive into Reasoning Large Language Models
- Blog: Hierarchical Vision Language Action Model Using Success and Failure Demonstrations
- Blog: RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy
- Blog: ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation
- Blog: LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop
- Blog: GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
- Blog: Chain of Thought Prompting Elicits Reasoning in Large Language Models
- Blog: Inference Scaling for Long-Context Retrieval Augmented Generation
- Blog: The First International AI Safety Report
- Blog: Has GPT-5 Achieved Spatial Intelligence? An Empirical Study
- Blog: START: Self-taught Reasoner with Tools
- Blog: Process Reward Models That Think
- Blog: Test Time Scaling for Neural Processes
- Blog: Integrative Decoding: Improve Factuality via Implicit Self-consistency
- Blog: Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling
- Blog: Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification
- Blog: Towards an AI co-scientist
- Blog: Evaluating Step-by-step Reasoning Traces: A Survey
- Blog: Scaling Auditory Cognition via Test-Time Compute in Audio Language Models
- Blog: Scaling Properties of Diffusion Models for Perceptual Tasks
Showing 60 of 819 papers.
History & citation
Current · Permanent link
- The Limits of Inference Scaling with Imperfect Verifiers merged into this direction (53% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_inference_time_compute_scaling_test_time_334ddc9c,
title = {inference-time compute scaling (test-time compute scaling)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/inference-time-compute-scaling-test-time-compute-scaling/rdr_334ddc9cd5454925a854e0e444f1763b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_inference_time_compute_scaling_test_time_334ddc9c_v2,
title = {inference-time compute scaling (test-time compute scaling)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/inference-time-compute-scaling-test-time-compute-scaling/rdr_334ddc9cd5454925a854e0e444f1763b/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}