AgibotChina2026

BFM

Key figures as stated by the developer

0 of 7 key figures stated

Not stated: Model type · Controls · Inputs · Access · Parameters · Base model · Licence

Full specifications

2 of 14 fields stated

The letter points to the source at the foot of the page. Fields without a figure are dashed: the developer does not state them — that is not the same as zero, and not the same as no.
Field	Value	Source and caveats
Release
Released	17 April 2026	[A] "SHANGHAI, CHINA - April 17, 2026" ⁠A
Input and output
Model type	not stated	Note AGIBOT's own name is "BFM (Behavioral Foundation Model)"; it does not call it a vision-language-action or world action model. ⁠A
Inputs	not stated	Note AGIBOT: BFM imitates human movements "from a single demonstration or short video". ⁠A
Controls	not stated	Note Listed under locomotion, without naming the controlled body: "enabling robots to move with human-like fluidity and adaptability in the physical world". ⁠A
Degrees of freedom controlled	not stated
Size and speed
Parameters	not stated
Control rate	not stated
Where it runs and what it is built on
On robot or cloud	not stated
Base model	not stated
Openness
Access	not stated
Licence terms	not stated
Licence	not stated
The developer’s own claims
Learns new tasks	from a few examples	Developer claim: BFM "teaches robots to imitate human movements instantly from a single demonstration or short video". ⁠A
Works across robots	not stated	Yes only if the developer itself says the model runs on different robot models, for example robots from two manufacturers or two of one manufacturer’s models. Several units of the same robot do not count.

How to read the figures

50HzA: The letter in the grey square after a figure points to the source the figure came from. Pages with several sources carry several letters.

What the data labels mean

Notes

AGIBOT presented BFM as one of eight foundation models at its 2026 Partner Conference.
AGIBOT published a successor, BFM-2, on its Chinese website on 26 May 2026.

VersionsBFMBFM-2

The developer has released this model in several versions. Each figure applies to the version its source names.

Versions and notes in the key figures (3)

Model type

Note AGIBOT's own name is "BFM (Behavioral Foundation Model)"; it does not call it a vision-language-action or world action model.

Controls

Note Listed under locomotion, without naming the controlled body: "enabling robots to move with human-like fluidity and adaptability in the physical world".

Inputs

Note AGIBOT: BFM imitates human movements "from a single demonstration or short video".

Sources

A Primary source. www.agibot.com/article/231/detail/63.html · Retrieved 2026-10-19

One line per source, not per figure: a source has one retrieval date. The letter beside a figure points to the line it came from.