# AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluation

arXiv: https://arxiv.org/abs/2610.03896 · HTML: https://mlsanity.com/paper/2610.03896/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 24 of 24)

- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [Non-stochastic Best Arm Identification and Hyperparameter Optimization](https://mlsanity.com/paper/1502.07943/) (2015)
- [On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice](https://mlsanity.com/paper/2007.15745/) (2020)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design](https://mlsanity.com/paper/2501.08603/) (2025)
- [LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics](https://mlsanity.com/paper/2405.20132/) (2024)
- [HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs](https://mlsanity.com/paper/2412.14995/) (2024)
- [A Systematic Survey on Large Language Models for Algorithm Design](https://mlsanity.com/paper/2410.14716/) (2024)
- [AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization](https://mlsanity.com/paper/2602.20133/) (2026)
- [EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Design](https://mlsanity.com/paper/2508.03082/) (2025)
- [Devstral: Fine-tuning Language Models for Coding Agent Applications](https://mlsanity.com/paper/2509.25193/) (2025)
- [HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization](https://mlsanity.com/paper/2506.07972/) (2025)
- [Efficient Heuristics Generation for Solving Combinatorial Optimization Problems Using Large Language Models](https://mlsanity.com/paper/2505.12627/) (2025)
- [HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design](https://mlsanity.com/paper/2508.13333/) (2025)
- [Generalizable Heuristic Generation Through LLMs with Meta-Optimization](https://mlsanity.com/paper/2505.20881/) (2025)
- [Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets](https://mlsanity.com/paper/2608.08189/) (2026)
- [Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution](https://mlsanity.com/paper/2606.08904/) (2026)
- [Dynamically Allocating Evaluation Effort for Model Ranking](https://mlsanity.com/paper/2608.03437/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used for automated algorithm design. However the computational cost of evaluating the generated algorithms can be excessive. We consider the common LLM-driven automated algorithm design (LLM4AD) setting in which a candidate algorithm is evaluated by aggregating its performance over a shared set of training instances. This instance-wise structure raises a natural question: must every candidate be evaluated on the entire instance set before deciding whether it remains competitive? Taking inspiration from algorithm configuration, we introduce AdaEva, a drop-in adaptive partial-evaluation framework that progressively evaluates candidates on larger subsets of the same instance pool and eliminates unpromising candidates as evidence accumulates. Importantly, AdaEva leaves the underlying LLM4AD procedure and per-instance evaluator unchanged and requires no prior knowledge about instance difficulty. We instantiate this idea using successive halving (AdaEva-S) and statistical racing (AdaEva-R), and evaluate both mechanisms across three representative LLM4AD frameworks, multiple LLM backbones, and optimization domains spanning combinatorial and continuous black-box optimization. Under matched evaluation budgets, AdaEva more reliably balances evaluation effort across candidates than fixed partial-evaluation strategies, yielding strong search efficiency and anytime performance together with improved held-out generalization across the evaluated settings.