Embodied AI for Scientific Discovery: From Physical Action to Scientific Evidence
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-08
Terminology
Sources
- BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Learning Interactive Real-World Simulators
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
- CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
- Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
- ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
- WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
- Large Language Models to Enhance Bayesian Optimization
- Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
- Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
- Genie: Generative Interactive Environments
- Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Benchmarking Autonomy in Scientific Experiments: A Hierarchical Taxonomy for Autonomous Large-Scale Facilities
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors
- ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation
- Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement
- Batch Bayesian Optimization via Local Penalization
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents