ASPIRE: An Agentic System-Identification Platform for Iterative Reasoning and Exploration
ASPIRE: An Agentic System-Identification Platform for Iterative Reasoning and Exploration
This paper introduces ASPIRE, a framework for nonlinear system identification where a large language model agent autonomously selects and executes identification methods. The system constructs closed-form models from measured data, optionally supplemented by physical descriptions and requirements. Evaluated on three systems (mobile robot, rotational system with dry friction, laboratory fermenter) across 30 runs, ASPIRE produced valid models at a cost of $0.96 to $3.38 per run. An author assessment found that model interpretations and documentation satisfied 132 of 150 items for recommended models, though nine models contained inaccurate or unsupported claims about structure selection.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S3
Reported numbers
dollars per run
0.96–3.38
View original evidence
wing the agent to ask questions and the user to request further analyses and identification rounds. We evaluate ASPIRE on three measured systems: a mobile robot, a rotational system with dry friction, and a laboratory fermenter. Each system is tested with and without a description, in five runs per task. All 30 runs delivered valid models, at a cost of 0.96 to 3.38 US dollars per run. An assessment by the authors fou
Open source S4
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
red data, optionally supplemented by a system description, the intended use of the model, and physical requirements expressed formally or in natural language. Each model includes its parameters, an estimation record, an interpretation of its terms, and an error evaluated on test data inaccessible to the agent. Formal physical requirements are verified independently. ASPIRE operates autonomously or interactively, allo
Open source S3
wing the agent to ask questions and the user to request further analyses and identification rounds. We evaluate ASPIRE on three measured systems: a mobile robot, a rotational system with dry friction, and a laboratory fermenter. Each system is tested with and without a description, in five runs per task. All 30 runs delivered valid models, at a cost of 0.96 to 3.38 US dollars per run. An assessment by the authors fou
Open source S4
nd that, for the 30 models recommended by the agent, one per run, the interpretation of the model and the documentation of its structure selection and parameter estimation fully satisfied 132 of 150 assessed items and partly satisfied 18. The most frequent discrepancy, found in nine models, concerned inaccurate or unsupported claims about model structure selection.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org