用比赛评分机制在1500次评估内让智能体自动进化，效果优于现有方法。
RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets
- 用埃洛竞赛代替传统验证，边比拼边进化，省下评估资源。
- 在四个任务中三胜一负，最高将准确率从27.8%提升至65.8%。
- 适合想低成本打造复杂智能体的研究者和开发者使用。
2026年，基于大模型的智能体演化系统引发广泛关注，如GEPA和Autoresearch已证明大模型可迭代优化提示、代码与架构。当评估成本高昂（如需人工判断或多次大模型调用）时，核心问题浮现：在相同初始条件与目标下，何种优化算法在固定评估预算内表现最佳？本文首次系统比较三种范式——埃洛竞赛选择（RoboPhD）、基于帕累托的选择（GEPA）与贪婪爬山（Autoresearch），在抽象推理、云调度、SQL生成和金融问答四个基准上，均限定1,500次评估。RoboPhD引入无验证演化：不划分训练/验证集，直接在训练数据上通过埃洛竞赛同时评估并驱动进化。所有系统从带诊断打印语句的种子智能体出发，演化出可自我监测的智能体，为后代提供更丰富的调试信息。采用单一默认配置，RoboPhD在三个任务中胜过另两者，仅在最简单任务中落败（该任务最优解仅需90行以下代码）。在ARC-AGI上，它将22行种子代码演化为1,013行多策略系统，使用Gemini 3.1 Flash Lite求解器，准确率从27.8%提升至65.8%。我们开源RoboPhD工具包，含简单的optimize_anything()接口，支持多样化复杂智能体的演化。
原文摘要 · Abstract (English)
2026 has brought an explosion of interest in LLM-guided evolution of agentic artifacts, with systems like GEPA and Autoresearch demonstrating that LLMs can iteratively improve prompts, code, and agent architectures across diverse domains. As adoption accelerates, a central question emerges: given the same information, the same seed agent, and the same objective, which optimization algorithm yields the best results under the same evaluation budget? This question becomes critical when evaluations are expensive, such as when they require human judgment or multiple LLM calls. We present the first systematic comparison of three optimization paradigms -- Elo tournament selection (RoboPhD), Pareto-based selection (GEPA), and greedy hill-climbing (Autoresearch) -- across four benchmarks spanning abstract reasoning, cloud scheduling, SQL generation, and financial QA, all under a fixed budget of 1,500 evaluations. RoboPhD introduces validation-free evolution: instead of splitting the budget between training and validation, it uses Elo competition on training data to simultaneously evaluate agents and drive evolution. All three systems receive seed agents with diagnostic print() statements that evolution can grow, enabling self-instrumenting agents that develop increasingly informative diagnostics for the benefit of their evolutionary successors. Using a single default configuration, RoboPhD outperforms both GEPA and Autoresearch on three of four benchmarks, losing only on the simplest task, where the winning solution (from our Autoresearch adaptation) required under 90 lines of code. On ARC-AGI, RoboPhD evolves a 22-line seed agent into a 1,013-line multi-strategy system, improving accuracy from 27.8% to 65.8% using Gemini 3.1 Flash Lite as the solver. We release RoboPhD as a versatile toolkit under the MIT license with a simple optimize_anything() API for evolving diverse complex agents.
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。