EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs

• URL: http://arxiv.org/abs/2604.15787v1
• Date: Fri, 17 Apr 2026 07:48:17 GMT
• Title: EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs
• Abstract summary: We introduce EVIL (textbfEVolving textbfInterpretable algorithms with textbfLLMs) to discover simple, interpretable algorithms for dynamical systems inference.<n>Rather than training neural networks on large datasets, EVIL evolves pure Python/NumPy programs that perform zero-shot, in-context inference across datasets.
• Score: 1.0152838128195467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce EVIL (\textbf{EV}olving \textbf{I}nterpretable algorithms with \textbf{L}LMs), an approach that uses LLM-guided evolutionary search to discover simple, interpretable algorithms for dynamical systems inference. Rather than training neural networks on large datasets, EVIL evolves pure Python/NumPy programs that perform zero-shot, in-context inference across datasets. We apply EVIL to three distinct tasks: next-event prediction in temporal point processes, rate matrix estimation for Markov jump processes, and time series imputation. In each case, a single evolved algorithm generalizes across all evaluation datasets without per-dataset training (analogous to an amortized inference model). To the best of our knowledge, this is the first work to show that LLM-guided program evolution can discover a single compact inference function for these dynamical-systems problems. Across the three domains, the discovered algorithms are often competitive with, and even outperform, state-of-the-art deep learning models while being orders of magnitudes faster, and remaining fully interpretable.

Related papers

• Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review [59.856222854472605]
  This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models.<n> practical applications in fields such as biology often require sample generation that maximizes specific metrics.<n>We discuss (1) fine-tuning methods combined with inference-time techniques, (2) inference-time algorithms based on search algorithms such as Monte Carlo tree search, and (3) connections between inference-time algorithms in language models and diffusion models.
  arXiv  Detail & Related papers  (2025-01-16T17:37:35Z)
• Continual Learning for Multimodal Data Fusion of a Soft Gripper [1.0589208420411014]
  A model trained on one data modality often fails when tested with a different modality.<n>We introduce a continual learning algorithm capable of incrementally learning different data modalities.<n>We evaluate the algorithm's effectiveness on a challenging custom multimodal dataset.
  arXiv  Detail & Related papers  (2024-09-20T09:53:27Z)
• From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models [63.188607839223046]
  This survey focuses on the benefits of scaling compute during inference. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation.
  arXiv  Detail & Related papers  (2024-06-24T17:45:59Z)
• Distributive Pre-Training of Generative Modeling Using Matrix-Product States [0.0]
  We consider an alternative training scheme utilizing basic tensor network operations, e.g., summation and compression. The training algorithm is based on compressing the superposition state constructed from all the training data in product state representation. We benchmark the algorithm on the MNIST dataset and show reasonable results for generating new images and classification tasks.
  arXiv  Detail & Related papers  (2023-06-26T15:46:08Z)
• Explainable Lifelong Stream Learning Based on "Glocal" Pairwise Fusion [17.11983414681928]
  Real-time on-device continual learning applications are used on mobile phones, consumer robots, and smart appliances. This study presents the Explainable Lifelong Learning (ExLL) model, which incorporates several important traits. ExLL outperforms all algorithms for accuracy in the majority of the tested scenarios.
  arXiv  Detail & Related papers  (2023-06-23T09:54:48Z)
• Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP [81.00800920928621]
  We study representation learning in partially observable Markov Decision Processes (POMDPs) We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) We then show how to adapt this algorithm to also work in the broader class of $gamma$-observable POMDPs.
  arXiv  Detail & Related papers  (2023-06-21T16:04:03Z)
• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• SurvLIMEpy: A Python package implementing SurvLIME [1.0689187493307983]
  We present SurvLIMEpy, an open-source Python package that implements the SurvLIME algorithm. The package supports a wide variety of survival models, from the Cox Proportional Hazards Model to deep learning models such as DeepHit or DeepSurv.
  arXiv  Detail & Related papers  (2023-02-21T09:54:32Z)
• Learned Factor Graphs for Inference from Stationary Time Sequences [107.63351413549992]
  We propose a framework that combines model-based algorithms and data-driven ML tools for stationary time sequences. neural networks are developed to separately learn specific components of a factor graph describing the distribution of the time sequence. We present an inference algorithm based on learned stationary factor graphs, which learns to implement the sum-product scheme from labeled data.
  arXiv  Detail & Related papers  (2020-06-05T07:06:19Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.