# Greedy Is a Strong Default: Agents as Iterative Optimizers

arXiv: https://arxiv.org/abs/2603.27415 · HTML: https://mlsanity.com/paper/2603.27415/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 11 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 4 of 4)

- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Large Language Models to Enhance Bayesian Optimization](https://mlsanity.com/paper/2402.03921/) (2024)
- [EvoPrompting: Language Models for Code-Level Neural Architecture Search](https://mlsanity.com/paper/2302.14838/) (2023)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)

## Abstract (arXiv)

Classical optimization algorithms--hill climbing, simulated annealing, population-based methods--generate candidate solutions via random perturbations. We replace the random proposal generator with an LLM agent that reasons about evaluation diagnostics to propose informed candidates, and ask: does the classical optimization machinery still help when the proposer is no longer random? We evaluate on four tasks spanning discrete, mixed, and continuous search spaces (all replicated across 3 independent runs): rule-based classification on Breast Cancer (test accuracy 86.0% to 96.5%), mixed hyperparameter optimization for MobileNetV3-Small on STL-10 (84.5% to 85.8%, zero catastrophic failures vs. 60% for random search), LoRA fine-tuning of Qwen2.5-0.5B on SST-2 (89.5% to 92.7%, matching Optuna TPE with 2x efficiency), and XGBoost on Adult Census (AUC 0.9297 to 0.9317, tying CMA-ES with 3x fewer evaluations). Empirically, on these tasks: a cross-task ablation shows that simulated annealing, parallel investigators, and even a second LLM model (OpenAI Codex) provide no benefit over greedy hill climbing while requiring 2-3x more evaluations. In our setting, the LLM's learned prior appears strong enough that acceptance-rule sophistication has limited impact--round 1 alone delivers the majority of improvement, and variants converge to similar configurations across strategies. The practical implication is surprising simplicity: greedy hill climbing with early stopping is a strong default. Beyond accuracy, the framework produces human-interpretable artifacts--the discovered cancer classification rules independently recapitulate established cytopathology principles.