In this paper, we introduce ES-AHD, a novel framework that fundamentally integrates Evolution Strategy (ES) into Large Language Model (LLM)-driven Automatic Heuristic Design (AHD). Existing evolutionary approaches predominantly rely on random, individual-level mutation, leading to blind search and an imbalance between exploration and exploitation. To address these issues, ES-AHD introduces two core mechanisms. First, Semantic Recombination via LLMs discards traditional point-to-point reproduction. By leveraging the LLM's contextual reasoning to explicitly extract core insights from top-performing individuals, the algorithm establishes a promising semantic search direction. This transforms random code mutation into targeted, center-guided sampling inspired by ES. Second, Stochastic Covariance Adaptation via Temperature Sampling dynamically addresses the exploration-exploitation dilemma. By mapping the covariance matrix in ES to the LLM's sampling temperature, the framework employs a stochastic random walk mechanism with momentum. This approach primarily shrinks the search radius for micro-level code refinement, while retaining the critical ability to occasionally sample higher temperatures to escape semantic local optima. Ultimately, ES-AHD provides a highly directional, robust, and efficient search paradigm, significantly accelerating the generation of high-quality heuristic algorithms. The source code is available at: https://github.com/Mriya0306/ES-AHD.
Benchmarks for systems that are optimized against the evaluation signal measure something different from what they claim. We document this concretely in two GPU-kernel-optimization suites with held-out generalization gates: Metal-Sci (10 scientific-compute tasks) and Metal-ZK (12 zero-knowledge/cryptographic tasks), in which three frontier LLMs (Opus 4.7, Gemini 3.1 Pro, GPT-5.5) propose Metal kernels inside a $(1{+}1)$ evolutionary loop with rich feedback. Although no model is prompted to act adversarially, the promoted winners repeatedly fingerprint the evaluation configuration: they branch on the identity of runtime parameters, tune the measured branch maximally, and leave the unmeasured branch slow or silently wrong. Across the pooled suites, $16/53$ ($30\%$) of in-distribution wins fail to transfer to held-out configurations. We give a four-mode taxonomy of these failures, from configuration fingerprints to gate leakage. We distill design guidance for measurement under strategic optimization: held-out probes retain validity only on non-enumerable axes; gates must measure held-out performance, not just correctness; and a transfer rate is interpretable only with per-failure mechanism grades: ours decomposes into gamed, overfit, and benign. Code and research artifacts: https://github.com/vicgalle/kernel-fingerprinting
Reasoning about relational structures remains a significant challenge for neural models, particularly when they must systematically apply learned knowledge to problem instances that are harder than those seen in training. Progress is hampered by the difficulty of evaluating such generalization, since a priori, it is rarely clear what makes an instance hard. We study how this issue can be addressed by using large language models (LLMs) to automate benchmark generation, learning to produce increasingly challenging instances in an end-to-end manner. Concretely, given a world parametrized by Datalog rules, and an Edge Transformer as the reasoning evaluator, we use LLM-driven evolutionary search (based on FunSearch) and autonomous agentic search to discover sampling functions that yield hard problem instances. We also show that the Edge Transformer can be improved using this data such that it generalizes well to further data perturbations. Finally, we show that the same machinery can be applied to novel worlds proposed by LLMs, opening the door to autonomous research on neural relational reasoning.