Evo-B&B is a new evolutionary framework that jointly evolves branching and node selection policies for Mixed-Integer Linear Programming (MILP) using large language model guidance and end-to-end SCIP solving feedback. It introduces a behavior-aware multi-island mechanism that measures policy similarity based on branching and node-selection behaviors to preserve population diversity and reduce redundant evaluations. Experiments on four standard MILP benchmarks show that Evo-B&B achieves competitive solving performance, generalizes to larger instances, and that joint evolution and behavior-aware diversity management are effective.
By Jiayu Chen, Chentong Chen, Yuhan Liu, Ye Fan, Jianyong Sun, Jialong Shi
The paper introduces EMO-STA, a two‑stage evolutionary multi‑task optimization framework for large‑language‑model (LLM) guided program discovery. First, it evolves a shared archive of executable programs across a family of related tasks; then it adapts selected shared candidates to each target task using strategies such as warm‑starting, best‑average, or best‑per‑task adaptation. Experiments on eight diverse task families show that EMO‑STA outperforms single‑task evolution under matched budgets, with balanced shared and adaptation budgets yielding the best results and shared evolution helping to reduce overfitting in low‑evidence scenarios.
By Halil Alperen Gozeten, Xuechen Zhang, Emrullah Ildiz, Ege Onur Taga, Tara Javidi, Samet Oymak
TurboEvolve is a multi‑island evolutionary framework that enhances LLM‑driven program evolution by improving sample efficiency and stability within fixed API‑cost budgets. It introduces Verbalized Sampling to generate multiple diverse candidates in a single LLM call, an adaptive scheduler that adjusts the number of offspring based on progress, and island‑aware initialization that clusters seed programs and mixes subpopulations with elitist preservation. The authors also provide a reusable cross‑task solution‑pool dataset and demonstrate that TurboEvolve achieves better cost‑quality trade‑offs and more stable performance on mathematical discovery and GPU‑kernel optimization tasks compared to controlled baselines.
By Yang Yang, Zining Zhong, Jindong Li, Jiemin Wu, Kaishen Yuan, Wenshuo Chen, Menglin Yang, Yutao Yue
arXiv:2608. 05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly.
By Sichun Luo, Yi Huang, Guanzhi Deng, Haibo Wang, Haochen Luo, Lei Li, Zefa Hu, Junlan Feng, Qi Liu
arXiv:2606. 25198v2 Announce Type: replace Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning.
By Antonis Antoniades, Deepak Nathani, Ritam Saha, Alfonso Amayuelas, Ivan Bercovich, Zhaotian Weng, Vignesh Baskaran, Kunal Bhatia, William Yang Wang
Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related tasks and domains. However, existing LLM-driven evolutionary frameworks largely discard such knowledge, repeatedly rediscovering similar ideas and limiting opportunities for cross-run and cross-task learning.
The paper critiques the common practice of evaluating large‑language‑model (LLM) evolutionary search methods using a single seed and fixed iteration budget, arguing that this approach is insufficient. By testing three search strategies across five optimization tasks and varying both the number of seeds (width) and iterations (depth), the authors find that optimal budget allocation depends on the strategy, task, and total budget, and that strategy rankings shift with different budgets. They propose a measurement protocol that maps the seeds‑by‑iterations frontier and offers practical guidance for researchers.
By Tal Oved, Roi Pony, Oshri Naparstek, Udi Barzelay
The paper introduces TOPOFE, a framework that treats automatic feature engineering for tabular data as a graph-structured multi-island evolutionary search. Each island explores a semantically coherent family of transformations using LLM-guided mutation and crossover, while a Prompt Adaptation Memory steers proposals based on accept/reject feedback. TOPOFE dynamically learns a directed topology graph to coordinate cross-island transfer, enabling the discovery of compositional feature programs that outperform state‑of‑the‑art methods on 29 datasets and produce lower redundancy and higher representational coverage.
By Sha Li, Naren Ramakrishnan
Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and strong models under a fixed inference budget.
arXiv:2609.38349v1 Announce Type: cross
Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects lon...
By Prithwish Jana, Mononito Goswami, Hao Liu, Xinyu Li, Langlin Huang, Zhehui Huang, Zhishen Huang, Patrick Bl\"obaum, Anoop Deoras, Purak Jain, Nikos Kanakaris, Sahika Genc
arXiv:2608. 10795v1 Announce Type: new Abstract: Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related tasks and domains.
By Viktor Volkov, Valentin Khrulkov, Andrey V. Galichin, Danil Sivtsov, Nikita Glazkov, Olga Volkova, Konstantin Pchelin, Iaroslav Bespalov, Dmitry V. Dylov, Petr Anokhin, Ivan Oseledets
arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?
By Young-Jun Lee, Seungone Kim, Minki Kang, Alistair Cheong Liang Chuen, Zerui Chen, Seungho Han, Taehee Jung, Dongyeop Kang