Evolutionary Algorithms and Applications

Neueste Paper

• SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents

  Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zirui Zhou · 5. Oktober 2026

  Large language model (LLM)-driven evolutionary search is a powerful paradigm for automated program and algorithm discovery, yet existing systems are largely memoryless: each run explores from scratch, so agents repeatedly rediscover the same improvements and re-encounter the same dead ends. We intro…

• FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution

  Hui Chen, Xuan Qi, James Xu Zhao, Zhaopeng Feng, Shilong Liu, Kuang Xu, Pang Wei Koh, Bryan Hooi · 5. Oktober 2026

  LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization shou…

• Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis

  Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang, Lekang Jiang, SiYuan Ma, Qituan Zhang, Guo Chen, Linfeng Zhang · 5. Oktober 2026

  Generating progressively harder reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recursion reuses generated problems as seeds but leaves the construction harness unchanged. We present task-harness co-evolution, a framework for recursiv…

• Reliable Self-Evolution with Imperfect Proxy Rewards

  Kangjun Noh, Soyu Kim, Kyungwoo Song · 5. Oktober 2026

  Large language model (LLM)-based self-evolving search is a promising approach to scientific discovery. However, high-fidelity evaluation of every candidate is prohibitively expensive in some domains. Self-evolving systems in such settings therefore rely on low-cost but imperfect proxy rewards, which…

• LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery

  Bo Yuan, Wenqian Ye, Zelin Zhao, Lama Moukheiber, Henry Kautz, Aidong Zhang, Yongxin Chen · 2. Oktober 2026

  Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a si…

• Multi-Behavioral Evolved Substrates Through Neuromodulation and Activation Selection

  Romain Claret, Michael O'Neill, Paul Cotofrei, Kilian Stoffel · 2. Oktober 2026

  Open-ended artificial life systems must acquire diverse competencies from a single evolving genotype. Biological brains combine neuromodulation, which reconfigures circuits without changing connections, with diverse neuron types matched to specific computational roles. Can artificial evolution achie…

• G\"odel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement

  Ziqi Zhao, Fanqing Meng, Haocheng Lu, Lingxiao Du, Qiguang Chen, Mengkang Hu, Xiao-Ming Wu · 1. Oktober 2026

  Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves. While most existing RSI systems optimize external agent harnesses or prompts around a frozen base model, data-centric RSI directly updates the model's own parameters by training on agent-generated…

• Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests

  Tianyu Chen, Yasi Zhang, Ruiyi Wang, Xinran Zhao, Taoran Li, Mingyuan Zhou · 1. Oktober 2026

  Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewrite tools and control flow. In practice, a user hands the same endpoint heterogeneous requests whose effective solutions require different tools, reaso…

• Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents

  Kaixing Zhang, Changming Li, Yingdong Shi, Zheng Zhang, Kaitao Song, Wenjie Shi, Jingang Wang, Kan Ren · 1. Oktober 2026

  Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill evolution remains largely confined to the text space: an optimizer must diagnose success and failure patterns, and revise skills solely from…

• Do Self-Evolving Skills Generalize to Held-Out Tasks?

  Xihao Piao, Zifeng Wang, Zhen Chen · 1. Oktober 2026

  AI agents can externalize what they learn from past tasks into reusable \emph{skills}, such as procedures, checklists, code, or other executable artifacts, that can be retrieved and reused when solving new tasks. Self-evolving skill methods keep rewriting these skills after each round of practice on…

• Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization

  Chen Lu, Ke Xue, Siyuan Xu, Mingxuan Yuan, Chao Qian · 1. Oktober 2026

  Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorithms. Many successful algorithm-design agents adopt pure in-context evolutionary frameworks, but they may quickly plateau in domains that require spec…

• Component-Aware Feedback for Self-Evolving Programs

  Ethan Lin, Jinming Nian, Yi Fang · 1. Oktober 2026

  LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which component edits produced which fitness metric changes. Existing methods force the mutator LLM to infer the effect of prior edits from clutt…

• Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer

  Qiankai Xu · 1. Oktober 2026

  A harness is the code around a language-model agent that organizes prompts, calls tools, manages context, and controls execution. As models grow stronger, recent work has begun to let agents improve their own harnesses, a line of work known as self-evolving harnesses. In most existing methods, a sep…

• Evolving Towards Better Codes: LLM-Guided Search for High-Distance Binary Linear Codes

  Amal Seddas, Vladyslav Shashkov, Maryna Viazovska, Emmanuel Abbe · 30. September 2026

  Evolutionary program search driven by large language models (LLMs) has produced record-breaking constructions for open problems in combinatorics and beyond. We apply this approach to the longstanding problem of improving the best-known bounds for binary linear codes. Building on the EvoTune evolutio…

• Mixture of Self-Improving Branches For Agent Harness Optimization

  Haoyu Dong, Yuhang Zhou, Zihao Lin, Yifan Wu, Bo Peng, Mingyi Wang, Xiangjun Fan, Lizhu Zhang, Zhuokai Zhao · 30. September 2026

  Harness optimization provides a practical setting for recursive self-improvement (RSI), where agent-generated modifications inform subsequent changes through execution feedback. Recent work such as Meta-Harness implements this process through iterative code generation and evaluation, but retains a f…

• How Can Recommendation Feedback Evolve Agent Memory?

  Shanwen Mao, Mingming Li, Hao Zhang, Zhiheng Li, Yige Wang, Penghua Yu, Junxiong Zhu · 30. September 2026

  Content-generation agents continuously receive impressions, clicks, conversions, and negative feedback from recommendation systems, providing real-world outcome signals for memory evolution. However, these signals are delayed and noisy, confounded by audience composition, placement, and recommendati…

• SimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priors

  Jianghan Zhu, Cong Zhang, Rongjie Zhu, Chi Zhang, Zhiguang Cao · 30. September 2026

  Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuristics. However, the dominant paradigm embeds LLMs as narrow, fixed components, such as crossover or mutation, within heavily hand-engineered evolutio…

• SAGE: A Statistical Acceptance Gate for Self-Evolving Agents

  Yihao Wang, Linhan Xia, Rui Liu, Zhaofeng Zhang, Hongyu Wu, Yang Yang, Jinglu He, Yu Guo, Kai Lei · 30. September 2026

  Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and decision logic. This loop has two steps, an optimizer that proposes a candidate edit and a gate that accepts or rejects it. Prior work has concentr…

• Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training

  Yuyang Deng, Yu Wang, Jiayun Wang · 29. September 2026

  Self-evolving language models improve by generating tasks and learning from their own feedback, but adapting the task generator often requires a separate challenger-training loop. Can we generate tasks adapted to the current solver without explicitly training a challenger? We introduce \textbf{D}ire…

• JET: Judge-Guided Evolution at Test Time for Agent Programs

  Yao Long Teng, Jiayi Cai, Bo An · 29. September 2026

  An agent's executable program governs how it uses tools, processes observations, and responds to failures. Evolving this program at test time can help adaptation, but deciding which changes to retain is difficult when true rewards are unavailable. Execution traces provide evidence of agent behavior,…

• Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks

  Xiaojing Sun, Yuhan Zeng, Zihua She, Xiao Wang · 29. September 2026

  As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search. RSI typically relies on finite evaluation resources, such as fixed benchmarks, to determine which modifications are retained and what is proposed next. However, when these finite r…

• Not Every Term Adds New Structure: Sobolev Novelty for Symbolic Regression

  Boxiao Wang, Kai Li, Yuheng Jing, Tianyi Liu, Chen Li, Yifan Zhang, Jian Cheng · 29. September 2026

  Symbolic regression (SR) aims to discover compact and meaningful mathematical equations from data, but searching the vast combinatorial space of symbolic structures remains challenging. Existing methods typically guide this process using expression-level objectives, such as fitting error, which asse…

• SNIP++: Fine-Grained Symbolic-Numerical Alignment for Symbolic Regression

  Benjamin L\'eger, Shubham Gupta, Samy Mammeri, Kazem Meidani, Cem Subakan, Christian Gagn\'e · 29. September 2026

  Mathematical expressions and the numerical behavior they produce are two views of the same underlying function, and connecting them is central to scientific discovery. Symbolic Regression (SR) relies on this connection directly: it searches for an expression that reproduces a given behavior. Recent …

• MechBench: Can AI Scientific Agents Discover Mechanisms Beyond Phenomenal Laws?

  Zihan Yu, Jiadong Zhang, Jialin Cheng, Jingtao Ding, Yong Li · 29. September 2026

  Scientific discovery requires not only recovering mathematical laws that describe observable behavior, but also identifying the mechanisms that generate them. Existing benchmarks for symbolic regression and scientific agents primarily evaluate phenomenal-law recovery, leaving mechanism discovery lar…

• SRHarness: A Harness for Agentic Symbolic Regression

  Zihan Yu, Shixuan Zhou, Hao Huang, Jingtao Ding, Yong Li · 29. September 2026

  Recent agentic symbolic regression approaches increasingly rely on large language models to analyze data, select scientific operations, and refine hypotheses over long search trajectories. In such systems, performance depends not only on the underlying model and search strategy, but also on the runt…