SeisEvo is a method that uses a large language model (LLM) and multi‑agent search to evolve seismic data reconstruction algorithms rather than optimize a single result. Starting from a classical algorithm, the agents modify only user‑opened components, rejecting candidates that violate physical constraints and scoring the rest by execution. The resulting white‑box algorithms—such as a residual‑gated, phase‑aligned dip‑consistency projection for interpolation and a reliability‑grouped singular‑value shrinkage for simultaneous interpolation and denoising—outperform classic methods by several decibels and generalize to unseen data.
arXiv:2609.07983v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) have recently emerged as a promising approach for solving Partial Differential Equations (PDEs), offering a me...
arXiv:2607. 04440v1 Announce Type: cross Abstract: Seismic wavefield simulation is fundamental to seismology, but conventional finite-difference (FD) methods remain limited by numerical dispersion and stability constraints, which often require dense spatial grids and small time steps and thereby severely limit the effectiveness of iterative inversion workflows.
arXiv:2607. 16249v1 Announce Type: cross Abstract: Probabilistic seismic hazard and risk analyses are backbone to building codes, insurance pricing, and disaster management.
arXiv:2606. 04360v1 Announce Type: cross Abstract: Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient because they rely mainly on scalar feedback such as MSE.
arXiv:2607. 12122v1 Announce Type: new Abstract: We present an agentic approach to autonomous neural operator discovery based on an AI scientific community, which consists of a swarm of virtual laboratories that interact under a citation-based economy of influence.
arXiv:2608. 00316v1 Announce Type: new Abstract: Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by generic statistical priors.
The paper introduces DualViewEval, a benchmark compression technique for agent evaluation that jointly uses outcome and process signals to learn an exact-size miniset and predict full-benchmark scores. By analyzing large-scale trajectories, the authors identify six complementary process signals linked to final agent performance. Across five agent benchmarks and five baselines, DualViewEval achieves superior compression (24×–40×) and lower error rates, while also revealing capability differences among agents for efficient development.
arXiv:2607. 29626v1 Announce Type: new Abstract: As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important.
arXiv:2608. 27260v1 Announce Type: new Abstract: LLM agents increasingly rely on generated interaction data to learn how to interact with external environments.
arXiv:2606. 04261v1 Announce Type: new Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback.
The paper introduces FLARE‑T, a Transfer‑Enabled Forced Latent Autoencoder for Response Equations, which learns low‑dimensional latent dynamics from dense finite‑element simulations and calibrates them with sparse field observations. By mapping simulated sensor responses into a learned coordinate system, FLARE‑T improves multi‑depth acceleration predictions and pseudo‑acceleration spectra, reducing errors across various sensor locations and motion intensities. Evaluation on a layered‑soil centrifuge test and the Lotung field array demonstrates that FLARE‑T achieves comparable accuracy with different source models, indicating less reliance on precise prior calibration.
arXiv:2607. 06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures.