What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search

• URL: http://arxiv.org/abs/2604.19440v1
• Date: Tue, 21 Apr 2026 13:16:45 GMT
• Title: What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
• Abstract summary: We present a large-scale study of evolutionary search using large language models (LLMs)<n>We find that strong LLMs behave as local refiners, producing frequent incremental improvements while progressively localizing the search in semantic space.<n>Our results highlight the importance of trajectory analysis for understanding and improving LLM-based optimization systems.
• Score: 12.864972111640247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent work has demonstrated the promise of orchestrating large language models (LLMs) within evolutionary and agentic optimization systems. However, the mechanisms driving these optimization gains remain poorly understood. In this work, we present a large-scale study of LLM-guided evolutionary search, collecting optimization trajectories for 15 LLMs across 8 tasks. Although zero-shot problem-solving ability correlates with final optimization outcomes, it explains only part of the variance: models with similar initial capability often induce dramatically different search trajectories and outcomes. By analyzing these trajectories, we find that strong LLM optimizers behave as local refiners, producing frequent incremental improvements while progressively localizing the search in semantic space. Conversely, weaker optimizers exhibit large semantic drift, with sporadic breakthroughs followed by stagnation. Notably, various measures of solution novelty do not predict final performance; novelty is beneficial only when the search remains sufficiently localized around high-performing regions of the solution space. Our results highlight the importance of trajectory analysis for understanding and improving LLM-based optimization systems and provide actionable insights for their design and training.

Related papers

• Rectifying LLM Thought from Lens of Optimization [48.98086817378953]
  Long chain-of-thought (CoT) prompting enables thorough exploration and deliberation.<n>Despite advances, long-CoT LLMs often exhibit suboptimal reasoning behaviors.<n>We introduce RePro, a novel approach to refine LLM reasoning during post-training.
  arXiv  Detail & Related papers  (2025-12-01T17:41:08Z)
• A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving [26.501685261132124]
  Large Language Models (LLMs) are increasingly being explored for tackling optimization problems.<n>Despite rapid progress, the field still lacks a unified synthesis and a systematic taxonomy.<n>This survey addresses this gap by providing a comprehensive review of recent developments and organizing them within a structured framework.
  arXiv  Detail & Related papers  (2025-09-10T04:05:54Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems [19.586884180343038]
  OPT-BENCH is a benchmark designed to evaluate Large Language Models (LLMs) on large-scale search space optimization problems.<n> OPT-Agent emulates human reasoning when tackling complex problems by generating, validating, and iteratively improving solutions through historical feedback.
  arXiv  Detail & Related papers  (2025-06-12T14:46:41Z)
• Make Optimization Once and for All with Fine-grained Guidance [78.14885351827232]
  Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks.<n>L2O paradigms achieve great outcomes, e.g., refitting, generating unseen solutions iteratively or directly.<n>Our analyses explore general framework for learning optimization, called Diff-L2O, focusing on augmenting solutions from a wider view.
  arXiv  Detail & Related papers  (2025-03-14T14:48:12Z)
• Deep Insights into Automated Optimization with Large Language Models and Evolutionary Algorithms [3.833708891059351]
  Large Language Models (LLMs) and Evolutionary Algorithms (EAs) offer promising new approach to overcome limitations and make optimization more automated. LLMs act as dynamic agents that can generate, refine, and interpret optimization strategies. EAs efficiently explore complex solution spaces through evolutionary operators.
  arXiv  Detail & Related papers  (2024-10-28T09:04:49Z)
• EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty.<n>We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications.<n>Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• Large Language Model-Aided Evolutionary Search for Constrained Multiobjective Optimization [15.476478159958416]
  We employ a large language model (LLM) to enhance evolutionary search for solving constrained multi-objective optimization problems. Our aim is to speed up the convergence of the evolutionary population.
  arXiv  Detail & Related papers  (2024-05-09T13:44:04Z)
• Are Large Language Models Good Prompt Optimizers? [65.48910201816223]
  We conduct a study to uncover the actual mechanism of LLM-based Prompt Optimization. Our findings reveal that the LLMs struggle to identify the true causes of errors during reflection, tending to be biased by their own prior knowledge. We introduce a new "Automatic Behavior Optimization" paradigm, which directly optimize the target model's behavior in a more controllable manner.
  arXiv  Detail & Related papers  (2024-02-03T09:48:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.