用多样性搜索保存代码库状态，提升程序演化的效率与质量。
Loreley: Repository-Scale Program Evolution with Quality-Diversity Search
- 保留完整代码库状态，通过质量-多样性算法选择父代进行演化。
- 在48次任务中，顺序编辑表现最佳，但多样性方法仍具潜力。
- 适合研究代码自动演化、AI辅助开发的工程师与研究人员。
顺序代理搜索仅积累当前最优分支，放弃其他路径；独立提案保留多样性但需从头开始。Loreley则将完整代码库状态存入质量-多样性（QD）档案，作为后续编辑的父代或上下文。候选为隔离工作树中的Git提交，由项目提供的评估器判断。我们在匹配的Zstandard实验中对比了配置后的Loreley QD、顺序冠军编辑和独立根提案：每块7对，每策略每块48个物理候选（共1008个），初始状态仅根节点，各策略采用原生并发。验证在每个预算检查点选出胜者；隐藏代理测试集测量固定候选表现。在48次任务时，QD比顺序冠军低0.135%（95% BCa区间：-0.556%至+0.161%），比独立根高0.320%（-0.082%至+0.686%）。两者均未显示显著优势；顺序策略在48次任务的平均值与中位数最高。档案保留与后期采样确实发生。七次最终胜利中有四次的主父代祖先包含非现任状态（按回溯性单一现任规则仅适用于观察到的QD流）。加入灵感边后该数增至六，但未证明提供上下文导致了具体修改。此前三次能力试验生成了第四代多文件改进，涵盖两个Python库及一个独立的Zstandard修订。Loreley实现了预期的阶梯式演化机制，但在受控实验中未在48次任务时显示出终点优势。
原文摘要 · Abstract (English)
Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root. Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits. Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator. We compare configured Loreley QD, sequential champion editing, and independent root proposals in a matched Zstandard experiment: seven paired blocks and 48 physical candidate jobs per policy and block (1,008 total), with root-only initialization and each policy's native concurrency. Validation selected a winner at each budget checkpoint; an agent-hidden holdout measured the fixed candidate. At 48 jobs, QD was 0.135% below Sequential Champion (95% BCa interval for the paired effect: -0.556% to +0.161%) and 0.320% above Independent Root (-0.082% to +0.686%). Neither contrast established a QD advantage; Sequential had the highest observed 48-job mean and median. Archive retention and later sampling did occur. Four of seven final QD winners had a non-incumbent state in their primary-parent ancestry under a retrospective one-incumbent rule applied only to the observed QD stream. Including inspiration edges raised the count to six, without showing that supplied context caused an edit. Three earlier capability campaigns produced generation-4, multi-file improvements in two Python libraries and a separate Zstandard revision. Loreley engaged the intended stepping-stone mechanism, but the controlled experiment did not show an endpoint benefit at 48 jobs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。