ASPIRE: An Agentic System-Identification Platform for Iterative Reasoning and Exploration
cs.RO, cs.AI, cs.CL, cs.LG, cs.SY, eess.SY
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/erik-derner/aspire-sysid
Terminology
Sources
- LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
- LLM4ED: Large Language Models for Automatic Equation Discovery
- Symbolic Regression with a Learned Concept Library
- Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance
- DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
- An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery
- Autonomous LLM-driven research from data to human-verifiable research papers
- CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation
- AIDE: AI-Driven Exploration in the Space of Code
- Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
- Contemporary Symbolic Regression Methods and their Relative Performance
- ASPIRE: Agentic /Skills Discovery for Robotics
- In-Context Symbolic Regression: Leveraging Large Language Models for Function Discovery
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- ASIA: an Autonomous System Identification Agent
- LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation