# AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization

arXiv: https://arxiv.org/abs/2602.20133 · HTML: https://mlsanity.com/paper/2602.20133/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 30 of 32)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [Evolution through Large Models](https://mlsanity.com/paper/2206.08896/) (2022)
- [Learning to Discover at Test Time](https://mlsanity.com/paper/2601.16175/) (2026)
- [ThetaEvolve: Test-time Learning on Open Problems](https://mlsanity.com/paper/2511.23473/) (2025)
- [Evolving Deeper LLM Thinking](https://mlsanity.com/paper/2501.09891/) (2025)
- [Barbarians at the Gate: How AI is Upending Systems Research](https://mlsanity.com/paper/2510.06189/) (2025)
- [FLEX: Continuous Agent Evolution via Forward Learning from Experience](https://mlsanity.com/paper/2511.06449/) (2025)
- [Agent-Oriented Planning in Multi-Agent Systems](https://mlsanity.com/paper/2410.02189/) (2024)
- [Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI](https://mlsanity.com/paper/2507.14172/) (2025)
- [DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution](https://mlsanity.com/paper/2602.02919/) (2026)
- [PACEvolve: Enabling Progress-Aware Consistent Evolution](https://mlsanity.com/paper/2601.10657/) (2026)
- [FrontierCS: Evolving Challenges for Evolving Intelligence](https://mlsanity.com/paper/2512.15699/) (2025)

## Built on by (most cited first, 30 of 60)

- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://mlsanity.com/paper/2604.01658/) (2026)
- [Structured Scaling of AI Discovery Across Diverse Scientific Domains](https://mlsanity.com/paper/2604.19341/) (2026)
- [ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence](https://mlsanity.com/paper/2605.26340/) (2026)
- [AI co-mathematician: Accelerating mathematicians with agentic AI](https://mlsanity.com/paper/2605.06651/) (2026)
- [Recursive self-improvement of AI research agents](https://mlsanity.com/paper/2609.26457/) (2026)
- [Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization](https://mlsanity.com/paper/2604.23472/) (2026)
- [Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering](https://mlsanity.com/paper/2607.28568/) (2026)
- [When Does Continual Learning Require Learning](https://mlsanity.com/paper/2607.07847/) (2026)
- [LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search](https://mlsanity.com/paper/2605.09764/) (2026)
- [EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery](https://mlsanity.com/paper/2606.13662/) (2026)
- [Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks](https://mlsanity.com/paper/2606.29082/) (2026)
- [SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery](https://mlsanity.com/paper/2607.02807/) (2026)
- [Automated Discovery Has No Universally Superior Harness](https://mlsanity.com/paper/2607.18235/) (2026)
- [ASI-Evolve: AI Accelerates AI](https://mlsanity.com/paper/2603.29640/) (2026)
- [The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning](https://mlsanity.com/paper/2603.15914/) (2026)
- [PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents](https://mlsanity.com/paper/2605.07039/) (2026)
- [BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution](https://mlsanity.com/paper/2606.01286/) (2026)
- [Fantastic Adaptive Taxonomies and How to Use Them](https://mlsanity.com/paper/2607.16387/) (2026)
- [SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution](https://mlsanity.com/paper/2604.24372/) (2026)
- [FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale](https://mlsanity.com/paper/2605.14445/) (2026)
- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery](https://mlsanity.com/paper/2605.22613/) (2026)
- [Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization](https://mlsanity.com/paper/2604.25083/) (2026)
- [CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness](https://mlsanity.com/paper/2605.04097/) (2026)
- [Evolving Ensemble of Agents](https://mlsanity.com/paper/2605.09018/) (2026)
- [SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution](https://mlsanity.com/paper/2605.15308/) (2026)
- [Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems](https://mlsanity.com/paper/2606.02863/) (2026)
- [Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents](https://mlsanity.com/paper/2606.12674/) (2026)
- [Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty](https://mlsanity.com/paper/2606.25198/) (2026)

## Abstract (arXiv)

The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operators within evolutionary loops. While effective, these systems are currently governed by static schedules that fail to account for the non-stationary dynamics of the search process. This rigidity results in substantial computational waste, as resources are indiscriminately allocated to stagnating populations while promising frontiers remain under-exploited. We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem. AdaEvolve uses an "accumulated improvement signal" to unify decisions across three levels: Local Adaptation, which dynamically modulates the exploration intensity within a population of solution candidates; Global Adaptation, which routes the global resource budget via bandit-based scheduling across different solution candidate populations; and Meta-Guidance which generates novel solution tactics based on the previously generated solutions and their corresponding improvements when the progress stalls. We demonstrate that AdaEvolve consistently outperforms the open-sourced baselines across 185 different open-ended optimization problems including combinatorial, systems optimization and algorithm design problems.