符号回归老被单一大模型提示词卡住，这个A-SR让不同智能体分工盯不同失败信号，准确率从25%拉到48%，还开源蒸馏路子，值得看一眼。
A-SR是一个自演化的智能体框架，用于从数据中发现闭式方程，将控制单元从表达式编辑转为角色条件证据视图。在LLM-SRBench的四个LSR-Synth科学领域上，A-SR将Acc@0.01从基线25.79%提升至48.30%（基于Llama3.1-8B），A-SR-LoRA将Qwen3-4B的结果从24.58%提升至38.29%。在四个真实世界科学发现任务中，A-SR在8项报告指标中的7项上取得最佳归一化均方误差。框架通过在线评估器奖励策略和状态路由过程记忆，在单次运行中无需更新参数即可自适应搜索，跨运行轨迹还可蒸馏为开源LLM的角色条件先验。
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt. We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views. A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory. During search, evaluator feedback characterizes reliability and productivity, updates role-level utilities, and routes elite motifs, failure traces, and validity diagnostics to different agents. The framework self-evolves at two timescales: within a run, it adapts the search process without updating LLM parameters; across runs, recorded trajectories can be distilled into open-source LLMs as role-conditioned proposal priors. Averaged over the four LSR-Synth scientific domains in LLM-SRBench, A-SR improves Acc@0.01 over baselines from 25.79% to 48.30% with Llama3.1-8B, while A-SR-LoRA improves the corresponding Qwen3-4B result from 24.58% to 38.29%. On four real-world scientific discovery tasks, A-SR obtains the best in-distribution or out-of-distribution normalized mean squared error on 7 of 8 reported metrics.