Skip to content

Embodied AI for Scientific Discovery: From Physical Action to Scientific Evidence

Nov 2026 · 0 citations · 135 references
Computer Science

TL;DR

Evaluation is proposed that separates actions, valid experiments, campaigns and confirmed claims, framing open challenges as controlled comparisons with measurable failure conditions.

Abstract

Scientific experiments are increasingly selected, executed and interpreted by learned systems that act through physical interfaces. Robot learning builds physical competence, whereas AI for science chooses which experiment to run, each reporting different endpoints. This review treats their interface as one problem, embodied AI for science, where the experiment itself is partially observed: specimen state, apparatus state and measurement processes are latent, actions are costly and irreversible, and missingness depends on execution and outcome. We organize the literature by three closures operating at distinct levels: operational closure (the experiment realized is the one intended), epistemic closure (the result updates beliefs or selects subsequent experiments) and evidential closure (the record supports a claim). We analyze workflows through a record-linked evidence cycle - Record, Diagnose, Calibrate, Confirm - as analytic functions with feedback. A taxonomy crosses these closures with six delegated decisions and five embodiment classes. Our formulation separates commanded, realized and observed conditions and models diagnosis with explicit resource, risk and sample-change costs. We compare experiment-selection methods by terminal decision, review perception, protocol compilation, visuomotor policies, world models, recovery and transfer by evidence emission requirements, and compare chemistry, materials, biology, microscopy and field workflows by what their records establish. An appendix provides an evidence map of 28 workflows (26 physical, two software-boundary), characterizing validation pathways and claim confirmation requirements. We propose evaluation that separates actions, valid experiments, campaigns and confirmed claims, framing open challenges as controlled comparisons with measurable failure conditions.

View source

Similar papers

Open access Oct 2026

Experimental reasoning in large language models

Scientific reasoning requires interaction with the physical world: designing experiments, interpreting outcomes, and deciding what experiment should come next. Here we show that general-purpose large language models (LLMs) already possess substantial capabilities for experimental reasoning. We connected LLMs to a liqui...

Jeonghyeon Kim, P. Romero · 0 citations
Preprint Oct 2026

Labference: Benchmarking the Reasoning-Action Connection in Robotic Laboratories

Realizing Embodied AI for Science requires robots to translate experimental goals into reliable physical procedures, reducing hazardous and repetitive human work while generating evidence for scientific discovery. Although language-based planning and learned manipulation provide complementary capabilities, their integr...

Shi-Tong Liu, Xu Yang, J. Zhang et al. · 0 citations
Preprint Oct 2026

EmbodiedLab: Benchmarking Embodied Agents That Act to Know

This work introduces EmbodiedLab, a benchmark in which a robot must act to know, and evaluates six frontier models in their developers' coding agents with native observation and control, with added perception and motion planning, and with manipulation skills distilled from the strongest agents.

Hong-Cheng Gao, Ze Zheng, Alex Zhou et al. · 1 citation
Preprint Oct 2026

Towards a Systematic Study of Embodied System 2 over Full Task Execution Cycles

An embodied brain, or System 2, must turn an abstract goal into actions while discovering relevant scene conditions and checking whether executed skills achieved their intended effects. Open-loop evaluations cannot test observations shaped by an agent's decisions, while some closed-loop evaluations provide limited evid...

Yu-Xi Wei, Ye Fang, Shuai Yang et al. · 1 citation
#artificial intelligence Preprint Sep 2026

HarnessPAI: An Evolving Harness for Physical AI

The results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and reasoning, and action execution into a unified, verifiable, and feedback-driven system.

X. Wang, Wen-Hao Wu, Meng-Hao Zhang et al. · 14 citations · ⚡2
Preprint Oct 2026

EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence

EmbodiedEvo is a self-evolving coding agent that distills physical feedback into reusable code Skills and diagnostic Lessons that improves weaker executors and shows the largest gains on memory-dependent tasks and successful reuse of coordinated procedures.

Wen-Yi Li, Yi-Zhe Chi, You-Jie Zheng et al. · 6 citations · ⚡3

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.