mlsanityData to 14 Oct 2026

Agentic AI for Gravitational Wave Data Analysis: A Head-to-Head Comparison of Coding Agents Executing a Matched Filter Pipeline on Einstein Telescope Simulated Data

arXiv 2605.28916 ↗First posted 27 May 2026astro-ph.IM cs.AI cs.HCcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

We report a methodological study of agentic AI in gravitational-wave data analysis: two systems, Claude Code (Anthropic) and Codex (OpenAI), autonomously executed the same simple end-to-end pipeline on Einstein Telescope (ET) simulated data, on shared infrastructure and without human intervention. The object of study is the behaviour, reliability and auditability of the agents, not the physics output, used here as a controlled test case. The pipeline comprises power spectral density estimation from simulated ET noise, geometric template bank generation with IMRPhenomD waveforms, matched-filter recovery of 100 binary black hole injections, results generation, and LLM-assisted production of a LaTeX manuscript in Physical Review D style. Both agents received identical specifications and resources. The experiment was run twice: first with unrealistically loud injections, then with signals rescaled to a physically motivated SNR range. In both runs the results converged, with comparable detection efficiency and template bank size. The agents, however, behaved very differently: Claude Code finished in about 3.4 minutes with silent deviations from the specification, while Codex needed about 16 minutes across explicit self-correcting restarts, including an unsolicited optimization of the matched-filter inner loop. In the second run, a subtle difference in interpreting the SNR-range instruction produced a genuine scientific divergence: Claude Code silently raised the SNR floor to 8 (100% efficiency), while Codex followed the specification literally down to SNR 7 and recorded one missed detection. We discuss the implications - speed versus auditability, silent deviation versus explicit self-correction, instruction interpretation, and intermediate data representations in multi-model pipelines - for agentic AI in scientific workflows, within the limits of a single-pipeline, two-run benchmark.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 9 of its 73 references that are in the map. First posted on arXiv 27 May 2026.

Builds on

9 of 73 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy11 May
  2. 2026An agentic framework for gravitational-wave counterpart association in the multi-messenger era11 May
  3. 2026AI Agents Can Already Autonomously Perform Experimental High Energy Physics20 Mar

Other references · 6

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  3. 2022Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goalscited by 126
  4. 2021Goal Misgeneralization in Deep Reinforcement Learningcited by 123
  5. 2025Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detectioncited by 9
  6. 2022MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challengecited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
  2. 2026Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research
  3. 2025The AI Cosmologist I: An Agentic System for Automated Data Analysis
  4. 2025AI Agents for Ground-Based Gamma Astronomy
  5. 2026Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology
  6. 2026Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
  7. 2025Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data Analysis
  8. 2026Beyond a Better Score: Long-Horizon Agentic ML Development and Evaluation Protocol for Physics Time Series