Language Model-Guided Search Heuristics

Follow this topic Ask about this topic

Latest papers

23 papers9 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Verifier Noise Is a Temperature: Testing Tilt Predictions in Finite-Budget LLM-Guided Search
Nov 6, 2026Xiaomeng LiLarge Language Model-Guided Optimization Language Model-Guided Search Heuristics
Link Heart Limited, Houston, TX, USA
Depth or Description? When a One-Step Latent Score Replaces Lookahead in Proactive Information Acquisition
Nov 4, 2026Biswa SenguptaActive Information Gathering Value of Information
LLM Suite Team, JPMorgan Chase & Co.
CosmosAlpha: Multi-Relational Graph Search with Pareto-Guided Exploration for LLM-Driven Alpha Mining
Nov 3, 2026Zhan-He Wang, Zi-Yang Lang, Yi-Yang Li +2Alpha Factor Discovery Language Model-Guided Search Heuristics
Artificial Intelligence and Quantitative Finance Laboratory, School of Physical Sciences, University of Chinese Academy of Sciences · School of Physics and Astronomy, Shanghai Jiao Tong University · School of Fundamental Physics and Mathematical Sciences, Hangzhou Institute for Advanced Study, UCAS
Large Language Model-Assisted Adaptive Heuristic Search for Agile Earth Observation Satellite Scheduling
Nov 3, 2026He Wang, Yeye Liu, Ruijie Li +5Language Model-Guided Search Heuristics Metaheuristic Optimization
College of Intelligent Science and Engineering, Harbin Engineering University, Harbin 150001, China · School of Electrical and Control Engineering, North University of China, Taiyuan 030051, China · School of Electrical and Electronic Engineering, Shandong University of Technology, Zibo, 255000, China +3
Dream-COP: Guiding Algorithm Discovery for Combinatorial Optimization Problems in an Experience World
Oct 27, 2026Kuan Xu, Jianming Wang, Ni Zhang +3Automated Algorithm Discovery Combinatorial Optimization
Singapore Management University · University of Science and Technology of China · Eindhoven University of Technology +1
Retriever-Free Retrieval: Navigating Documents with Decision Models
Oct 26, 2026Chao Wan, Paul Jünger, Beixi Du +3Knowledge Retrieval in Language Models Information Retrieval
Department of Computer Science, Cornell University, New York, USA · ASAPP, New York, USA
DIGEST: Discovery-Guided LLM Tuning for Symbolic Regression
Oct 24, 2026Kaifeng Jin, Ruizhong Qiu, Zihao Li +5Symbolic Regression Large Language Model-Guided Optimization
University of Illinois Urbana-Champaign · Meta
CuraLoc: Repository-Level Fault Localization via Planned Code Inspection
Oct 22, 2026Sangeeta Warrier, Anush Sankaran, Ryen W. WhiteFault Localization Language Model-Guided Search Heuristics
Microsoft
Directing to Diversify: Multi-Directional Search for Automatic Heuristic Design
Oct 22, 2026Jianghan Zhu, Jianan Zhou, Fei Liu +4Automated Heuristic Design Language Model-Guided Search Heuristics
Singapore Management University · Nanyang Technological University · University of Zurich +3
TESS: LLM-guided Translation, Exploration, Simulation, and Search for Embodied Task Planning
Oct 19, 2026Peiran Xu, Yixiang Yang, Jinghan Li +4Robot Task Planning LLM Planning
Peking University · China Tower
P(Yes): 15 $\times$ Improvements via Test-Time Scaling of Decision Models
Oct 18, 2026Lev StamblerLLM Decision-Making Test-Time Scaling
Tear Labs · University of Maryland, College Park
IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization
Oct 16, 2026Maria Ana Cardei, Aniket Singh, Amir Moghadam +2Information Retrieval Hyperparameter Optimization
University of Virginia · University of California San Diego · Capital One
CIPHEUR: LLM-Guided Structural Search Control for Conflict-Graph Optimization
Oct 12, 2026Yuqing Cheng, Yan Jia, Yanjie Song +3Language Model-Guided Search Heuristics Combinatorial Optimization
National University of Defense Technology, Changsha, China · Dalian Maritime University, Dalian, China · Jiangsu University of Technology, Changzhou, China
MemEvo: Automatic Discovery of Streaming Video Memory Mechanisms
Sep 29, 2026Guohong Liu, Jialei Ye, Shanhui Zhao +2Memory-Augmented VLMs Language Model-Guided Search Heuristics
Institute for AI Industry Research, Tsinghua University · Peking University
AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search
Sep 6, 2026Peijia Qin, Ruiyi Zhang, Qi Cao +3Language Model-Guided Search Heuristics Automated Machine Learning
Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USA · Department of Medicine, University of California San Diego, La Jolla, CA 92093, USA
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
Aug 7, 2026Yingtao TianLanguage Model-Guided Search Heuristics Artificial Life
Sakana AI, Tokyo, Japan
Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners
Jun 23, 2026Anirban Das, Joanne Boisson, Irtaza Khalid +2Language Model-Guided Search Heuristics Relational Reasoning
Cardiff University · University of Pennsylvania
LLM-Aided A* Search in Non-Geometric Network Graphs
Jun 22, 2026Nouf Alabbasi, Esraa Ghourab, Omar AlhusseinLanguage Model-Guided Search Heuristics Tree Search
KU 6G Research Centre, Department of Computer Science, Khalifa University, Abu Dhabi, UAE
Learning the ARTS of Search for Automated Discovery
Jun 20, 2026Gurusha Juneja, Arnav Kumar Jain, Deepak Nathani +2Inference-Time Search Automated Algorithm Discovery
University of California, Santa Barbara · Université de Montréal and Mila- Quebec AI Institute
Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
May 15, 2026Sarah Martinson, Michael P. Brenner, Martyna Plomecka +3Epidemic Forecasting Language Model-Guided Search Heuristics
Google Research · School of Engineering and Applied Sciences, Harvard University · Google Deepmind +1
Hierarchical Task Network Planning with LLM-Generated Heuristics
May 8, 2026Felipe Meneguzzi, Alexandre Buchweitz, Augusto B. Corrêa +2Language Model-Guided Search Heuristics Hierarchical Planning
University of Aberdeen, UK · University of Oxford, UK · PUCRS, Brazil +2
VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problems
Oct 8, 2025André Hottung, Federico Berto, Chuanbo Hua +9Vehicle Routing Automated Heuristic Design
Bielefeld University · Radical Numerics · KAIST +6
SQL-o1: Automatic Text-to-SQL Program Synthesis via Self-Reward Heuristic Search
Feb 17, 2025Shuai Lyu, Haoran Luo, Ripeng Li +3Text-to-SQL LLM-Based Program Synthesis
School of Computer Science, Beijing University of Posts and Telecommunications, China. · College of Computing and Data Science, Nanyang Technological University, Singapore. · State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China.

Nov 6, 2026J/K move · Enter open · S save

Verifier Noise Is a Temperature: Testing Tilt Predictions in Finite-Budget LLM-Guided Search

Xiaomeng Li

Link Heart Limited, Houston, TX, USA

Large Language Model-Guided Optimization Language Model-Guided Search Heuristics Prompt Optimization

Open paper AskPDF arXiv

LLM-guided search loops propose a modified candidate, score it, and keep it if it scores better. When both candidates are re-scored at every comparison, as in the minibatch acceptance gates of prompt optimizers, keep-if-better is a reversible Markov chain if the score difference is logistic and the mutation operator is reversible, and its stationary law is the mutation equilibrium tilted by exp(beta f). For any continuous symmetric noise difference the same tilt is the stationary law of a small-step diffusion limit, with beta = 4F'(0); for a minibatch gate beta grows with the square root of the minibatch size. Caching the incumbent's score instead inflates the recorded score. We test the tilt as a prediction for LLM-guided program search, committing each prediction from calibration data before the search runs. The level after 150 steps rises with the minibatch size in six of seven settings, but its predicted value fails: on bin packing, search attains 62-88% of the predicted gain when the proposer edits the parent and 109-119% when it writes new heuristics. The attained fraction falls with the parent-child quality correlation of unselected mutation; a registered test on two new settings confirmed the direction, but not the quantitative agreement after a correction. Further registered tests found that runs started from a good program kept losing quality over 300 steps, more so from starts that search had selected, by a margin that passed its registered rule narrowly. Runs from different starts had not reached a common level, so whether the tilt describes the stationary law of LLM editing remains open. A registered test in prompt optimisation on frozen task-model scores failed: search exceeded the tilt, and the bin-packing relation did not transfer.