Inference-Time Search

Ask about this topic

Overview

Inference-time search studies how models can use additional computation at deployment to explore alternatives and improve their answers or decisions. Common approaches include best-of-N sampling, beam search and Monte Carlo tree search, guided by verifiers or reward models, with adaptive budgets, pruning, and memory used to focus effort. These methods are applied to mathematical reasoning, code and theorem proving, tool-using agents, planning, and scientific design, where stronger selection can matter as much as generating more candidates. A central tension is that search helps only when its guidance is informative: noisy scores can favor flawed paths, while broader exploration and verification cost time and compute.

Latest papers

CardsList

105 papers14 papers in the last four weeks, up 8% on the four weeks before. 0.1% of all new papers.

  1. PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection

    Apr 7, 2026Siyuan Cheng, Bozhong Tian, YanChao Hao +1Inference-Time SearchEfficient Language Model Reasoning

    Tencent PCG

  2. Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG

    Mar 30, 2026Davide Di GioiaRetrieval-Augmented GenerationEvidence Selection

  3. CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning

    Mar 30, 2026Siyuan Ma, Bo Gao, Zikai Xiao +6Efficient Language Model ReasoningMetacognition in Language Models

    Nanyang Technological University · Carnegie Mellon University · Zhejiang University +5

  4. A Priori Sampling of Transition States with Guided Diffusion

    Mar 26, 2026Hyukjun Lim, Soojung Yang, Lucas Pinède +3Diffusion Model GuidanceDiffusion Sampling

    Department of Materials Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, Republic of Korea. · Computational and Systems Biology, MIT, 77 Massachusetts Avenue, Cambridge, 02139, Massachusetts, USA. · Chimie ParisTech, PSL University, 11 rue Pierre et Marie Curie, Paris, 75005, France. +2

  5. FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization

    Mar 20, 2026Haijian Lu, Wei Wang, Jing LiuAutoformalizationInference-Time Search

    School of Artificial Intelligence, Xidian University, Xi’an, China · Beijing Institute for General Artificial Intelligence, Beijing, China

  6. More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search

    Mar 16, 2026Gal Dalal, Assaf Hallak, Gal Chechik +1Inference-Time Search

    NVIDIA Research · Bar-Ilan University · University of Groningen

  7. CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

    Mar 12, 2026Zi-Han Wang, Lam Nguyen, Zhengyang Zhao +4Computational CreativityCreativity Assessment

    Southern University of Science and Technology · Tsinghua University · Xi’an Jiaotong University +3

  8. How to make the most of your masked language model for protein engineering

    Mar 11, 2026Calvin McCarter, Nick Bhattacharya, Sebastian W. Ober +1Protein Language ModelsInference-Time Search

    BigHat Biosciences

  9. Efficient K-generalizable Learned Search

    Mar 6, 2026Yifan Peng, Jiafei Fan, Xingda Wei +7Inference-Time SearchGraph-Based Retrieval

    Shanghai Jiao Tong University · Boston University · Alibaba Group

  10. LiTS: A Modular Framework for LLM Tree Search

    Feb 28, 2026Xinzhe Li, Yaguang TaoInference-Time SearchTree Search

    RMIT University

  11. Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases

    Feb 19, 2026Zhao Tan, Yiji Zhao, Shiyu Wang +5Time Series QATemporal IR

    Jiangxi University of Finance and Economics · Griffith University · Yunnan University +2

  12. What If We Allocate Test-Time Compute Adaptively?

    Feb 1, 2026Ahsan Bilal, Ahmed Mohsin, Muhammad Umer +4Inference-Time SearchTest-Time Scaling

    University of Oklahoma, OK, USA · Stanford University, CA, USA · Universitat Pompeu Fabra, Barcelona, Spain +2

  13. Inference-Time Diversity in RL-Trained Lean Theorem Provers: A Diagnostic Study

    Jan 22, 2026Zachary BurtonInference-Time SearchRL for Language Model Reasoning

    Massachusetts Institute of Technology, Cambridge, MA, USA.

  14. Scalable Decision Making for Games of Imperfect Information

    Nov 10, 2025Samuel Sokota, Eugene Vinitsky, Hengyuan Hu +3Game-Playing AgentsInference-Time Search

    Carnegie Mellon University · NYU Tandon School of Engineering · Stanford University +1

  15. MASPRM: Multi-Agent System Process Reward Model

    Oct 28, 2025Milad Yazdani, Mahdi Mostajabdaveh, Zirui Zhou +1Multi-Agent LLM SystemsInference-Time Search

    Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V6T1Z4, Canada · Huawei Technologies Canada, Burnaby, BC V5C6S7, Canada