# Controlled Self-Evolution for Algorithmic Code Optimization

arXiv: https://arxiv.org/abs/2601.07348 · HTML: https://mlsanity.com/paper/2601.07348/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 12 Jan 2026.

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://mlsanity.com/paper/2305.16653/) (2023)
- [A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems](https://mlsanity.com/paper/2508.07407/) (2025)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents](https://mlsanity.com/paper/2508.02085/) (2025)
- [EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization](https://mlsanity.com/paper/2405.15189/) (2024)
- [EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code](https://mlsanity.com/paper/2505.13004/) (2025)
- [CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment](https://mlsanity.com/paper/2510.18471/) (2025)
- [Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization](https://mlsanity.com/paper/2505.23387/) (2025)
- [PurpCode: Reasoning for Safer Code Generation](https://mlsanity.com/paper/2507.19060/) (2025)
- [MaintainCoder: Maintainable Code Generation Under Dynamic Requirements](https://mlsanity.com/paper/2503.24260/) (2025)
- [Training Language Models to Generate Quality Code with Program Analysis Feedback](https://mlsanity.com/paper/2505.22704/) (2025)
- [Execution Guided Line-by-Line Code Generation](https://mlsanity.com/paper/2506.10948/) (2025)
- [Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs](https://mlsanity.com/paper/2508.07434/) (2025)

## Built on by (most cited first, 12 of 12)

- [EffiSkill: Agent Skill Based Automated Code Efficiency Optimization](https://mlsanity.com/paper/2603.27850/) (2026)
- [GEAR: Genetic AutoResearch for Agentic Code Evolution](https://mlsanity.com/paper/2605.13874/) (2026)
- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [AlphaSchema: Exploring the Space of Trading Semantics for LLM-Based Alpha Mining](https://mlsanity.com/paper/2607.26642/) (2026)
- [EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution](https://mlsanity.com/paper/2605.30105/) (2026)
- [Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents](https://mlsanity.com/paper/2608.01759/) (2026)
- [Self-Evolving Coding Agents](https://mlsanity.com/paper/2608.03392/) (2026)
- [Persistent Cross-Attempt State Optimization for Repository-Level Code Generation](https://mlsanity.com/paper/2604.03632/) (2026)
- [Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation](https://mlsanity.com/paper/2604.21950/) (2026)
- [MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution](https://mlsanity.com/paper/2609.38349/) (2026)
- [GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations](https://mlsanity.com/paper/2603.27306/) (2026)
- [Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization](https://mlsanity.com/paper/2609.14839/) (2026)

## Abstract (arXiv)

Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets. This inefficiency stems from initialization bias trapping evolution in poor solution regions, uncontrolled stochastic operations lacking feedback guidance, and insufficient experience utilization across tasks. To address these bottlenecks, we propose Controlled Self-Evolution (CSE), which consists of three key components. Diversified Planning Initialization generates structurally distinct algorithmic strategies for broad solution space coverage. Genetic Evolution replaces stochastic operations with feedback-guided mechanisms, enabling targeted mutation and compositional crossover. Hierarchical Evolution Memory captures both successful and failed experiences at inter-task and intra-task levels. Experiments on EffiBench-X demonstrate that CSE consistently outperforms all baselines across various LLM backbones. Furthermore, CSE achieves higher efficiency from early generations and maintains continuous improvement throughout evolution. Our code is publicly available at https://github.com/QuantaAlpha/EvoControl.