LLMs for Evolutionary Optimization

LLM: Large Language Model

Follow this topic Ask about this topic

Latest papers

41 papers14 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
Nov 5, 2026Qile Jiang, George Em KarniadakisLLMs for Evolutionary Optimization AI Agents for Scientific Discovery
DIVISION OF APPLIED MATHEMATICS, BROWN UNIVERSITY
Proof-Carrying Evolution: Black-Box Search, White-Box Flight
Oct 30, 2026Amit Jain, Sergio Sanchez-Hurtado, Victor Rodriguez-Fernandez +1Formal Verification Large Language Model-Guided Optimization
Massachusetts Institute of Technology. · Universidad Politécnica de Madrid.
Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization
Oct 30, 2026Shanglin Yang, Zhan ShiLarge Language Model-Guided Optimization LLMs for Evolutionary Optimization
Santa Clara University
Holistic Diversity Management in LLM-Guided Evolutionary Search
Oct 28, 2026Seockbean Song, Youngsik Yoon, Sungjae Lee +3Evolutionary Optimization LLMs for Evolutionary Optimization
Graduate School of AI, POSTECH · Department of CSE, POSTECH · Microsoft Research Asia
Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean
Oct 26, 2026Per Kristian LehreAutomated Algorithm Discovery Black-Box Optimization
School of Computer Science, University of Birmingham, UK
TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent
Oct 23, 2026Junlin He, Junzhang Zhu, Yudong Li +5Generative Recommendation Large Language Model-Guided Optimization
Platform and Content Group, Tencent, Shenzhen, China · The Hong Kong Polytechnic University, Hong Kong, China · McGill University, Montreal, Canada +1
AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments
Oct 22, 2026Ze-Yu Peng, Qing-Yu Lan, Zhan-He Wang +2LLMs for Evolutionary Optimization LLM-Based Program Synthesis
School of Physical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China. · International Centre for Theoretical Physics Asia-Pacific, University of Chinese Academy of Sciences, Beijing 100190, China. · Taiji Laboratory for Gravitational Wave Universe, University of Chinese Academy of Sciences, Beijing 100049, China. +2
GuideEvolve: Self-Evolving Agent Framework with Expert Guidance and 3Ts Mechanisms
Oct 21, 2026Meihong Jia, Yasemin Timar, Jonathan TawsSelf-Evolving Agents LLM Agent Self-Improvement
Amazon, Tokyo, Japan · Amazon Web Services, Luxembourg, Luxembourg
Lineage-Aware Search Control for LLM-Based Evolutionary Factor Mining
Oct 21, 2026Xintong Liu, Chenkai Zhang, Yanzhao Ma +1Alpha Factor Discovery LLMs for Evolutionary Optimization
Southern University of Science and Technology (SUSTech) Shenzhen, China
ExpEvolve: Structuring and Reusing Experience for Open-Ended Discovery
Oct 21, 2026Yongqiang Chen, Chenxi Liu, Deyu Zou +4AI Agents for Scientific Discovery Large Language Model-Guided Scientific Discovery
MBZUAI · Carnegie Mellon University · TMLR Group, Hong Kong Baptist University +2
SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
Oct 20, 2026Ha Minh Hieu, Tongyao Zhu, Do Xuan Long +1Large Language Model-Guided Scientific Discovery LLMs for Evolutionary Optimization
Hanoi University of Science and Technology · National University of Singapore
Beyond Experience: Knowledge-Guided Evolution for NPU Kernel Generation
Oct 20, 2026Xi Chen, Ming Shen, Haotian Yan +2LLMs for Evolutionary Optimization
Shenzhen Loop Area Institute (SLAI) · Guangzhou University · Shanghai Jiao Tong University +2
CVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery
Oct 19, 2026Ruodai Cui, Li NiuAutomated Heuristic Design Metaheuristic Optimization
Qualcomm Technologies, Inc. · The Hong Kong Polytechnic University · Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University
LLM-Based Evaluation Planning for Heterogeneous Optimization
Oct 17, 2026Nian Ran, Sebastian Brulin, Markus Olhofer +2Large Language Model-Guided Optimization Multi-Fidelity Optimization
The University of Manchester · UKRI AI Centre for Doctoral Training in Decision Making for Complex Systems · Honda Research Institute Europe
LLM Evolutionary Search Strategies Should be Compared by Tokens
Oct 13, 2026Tal Oved, Roi Pony, Oshri Naparstek +1LLMs for Evolutionary Optimization LLM Evaluation
IBM Research
SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents
Oct 1, 2026Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zirui ZhouMemory-Augmented Agents LLMs for Evolutionary Optimization
University of British Columbia · Huawei Technologies Canada
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Sep 30, 2026Young-Jun Lee, Jinheon Baek, Soyeong Jeong +5Large Language Model-Guided Optimization LLMs for Evolutionary Optimization
University of Minnesota · KAIST · Seoul National University +1
LLM-Driven Joint Evolution of Coupled Heuristics Components for Routing Optimization
Sep 2, 2026Juntao Wei, Yangming Zhou, Zhibin Jiang +1LLMs for Evolutionary Optimization Automated Heuristic Design
Antai College of Economics and Management, Shanghai Jiao Tong University, Shanghai 200030, China · Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai 200240, China
Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search
Aug 28, 2026Roberto I. Ono FilhoLLMs for Evolutionary Optimization LLM-Based Program Synthesis
Independent researcher
EvoMem: Memory-Augmented Evolution for Code Optimization
Aug 11, 2026Viktor Volkov, Valentin Khrulkov, Andrey V. Galichin +8Memory-Augmented Language Models Evolutionary Optimization
AXXX, Moscow, Russia · Applied AI Institute, Moscow, Russia · Lomonosov Moscow State University, Moscow, Russia
ELMER: Evolutionary Language Model that Explores and Refines
Aug 10, 2026Matthew Siper, Ahmed Khalifa, Julian TogeliusLarge Language Model-Guided Optimization Genetic Programming
Nof1, New York University · Nof1, University of Malta
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization
Aug 8, 2026Víctor GallegoBlack-Box Optimization Large Language Model-Guided Optimization
Komorebi AI Technologies
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
Aug 6, 2026Sichun Luo, Yi Huang, Guanzhi Deng +6Multi-Fidelity Optimization Evolutionary Optimization
1The University of Hong Kong · 2JIUTIAN Research, China Mobile · 3City University of Hong Kong +1
LLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms
Jul 6, 2026Georgios Laskaris, Reuben Brasher, Niki van Stein +3Automated Algorithm Discovery Evolutionary Optimization
Terra Quantum AG, Kornhausstrasse 25, 9000 St. Gallen, Switzerland · LIACS, Leiden University, Leiden, Netherlands
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Jun 27, 2026Young-Jun Lee, Seungone Kim, Minki Kang +5Large Language Model-Guided Optimization Evolutionary Optimization
University of Minnesota · Carnegie Mellon University · KAIST +3
Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution
Jun 3, 2026Can Gurkan, Forrest Stonedahl, Uri WilenskyLLMs for Evolutionary Optimization
Northwestern University Evanston, IL, USA
Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits
May 28, 2026Sixue Xing, Haoyu He, Kerui Wu +4Multi-Armed Bandits Evolutionary Optimization
University of Notre Dame · 2Northeastern University · University of Massachusetts Amherst +4
LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search
May 10, 2026Temoor TanveerEvolutionary Optimization Large Language Model-Guided Optimization
Independent Researcher
Relation Reasoning with LLMs in Expensive Optimization
Apr 30, 2026Ye Lu, Bingdong Li, Aimin Zhou +1Surrogate-Assisted Optimization Black-Box Optimization
Shanghai Institute of Al for Education, East China Normal University, Shanghai 200062, China
SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
Apr 27, 2026Sichun Luo, Yi Huang, Haochen Luo +7Automated Algorithm Discovery Evolutionary Optimization
1The University of Hong Kong · 2JIUTIAN Research, China Mobile · 3City University of Hong Kong

Nov 5, 2026J/K move · Enter open · S save

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

Qile Jiang, George Em Karniadakis

DIVISION OF APPLIED MATHEMATICS, BROWN UNIVERSITY

LLMs for Evolutionary Optimization AI Agents for Scientific Discovery LLM-Based Program Synthesis Multi-Agent LLM Systems LLM Agent Efficiency Latent Reasoning

Open paper AskPDF arXiv

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches. Each swarm studies the problem from a different angle. A novelty filter keeps the most distinct agent ideas by directly measuring the distances between the agents' hidden state vectors. Crossover of ideas happens naturally in latent space, as a summarizer agent receives the combined KV caches of all swarm members. On 21 problems in mathematical discovery and scientific computing, SwarmEvolve gets the highest average score and needs a median of only 3 to 8 minutes to reach the best scores that other state-of-the-art frameworks reach in 60 minutes. On several problems, SwarmEvolve with Qwen3 8B improves on the solutions that AlphaEvolve first found with frontier LLMs. Our work shows that agent swarms that communicate in latent space offer a fast, low-cost approach to program search for scientific problems.