MolmoAct2: Action Reasoning Models for Real-world Deployment

9 min read

A fully open VLA that turns embodied visual reasoning into fast continuous robot control through an action-aware VLM and a flow-matching expert.

BackboneMolmo2-ERER corpus3.3M examplesAction outputFlow matchingFAST vocabulary2,048 tokensBimanual data720 hoursReleaseWeights + data + code

architecture

A spatial VLM thinks; a dedicated expert moves

MolmoAct2 keeps visual-language reasoning in the backbone and hands smooth trajectory generation to a continuous action model.

Context tokens

Images / video

One or more robot camera views

Instruction

Natural-language task

Robot setup

Embodiment + control mode

Current state

256-bin discretized tokens

VLM backbone

Molmo2-ER

Molmo2 specialized for pointing, spatial QA, motion, multi-view correspondence, and egocentric reasoning.

Action-aware KV states

Next-token supervision keeps the backbone predicting discrete FAST actions during post-training.

K,V × layer

projected + detached

Continuous expert

DiT-style action expert

Cross-attends to matching VLM layers and learns a flow field from noisy actions to an executable trajectory.

Gaussian noise → velocity field → action chunk

Up to 30 timesteps × 32 action dimensions during post-training.

No target-token shortcut

The expert sees the task, observations, setup, and state, but its conditioning mask hides the target FAST action span.

Knowledge insulation

Flow loss trains the expert and KV adapters without flowing back into the VLM. Language-model loss keeps training the backbone.

training

Build the perception brain before asking it to move

The staged recipe avoids learning spatial reasoning, a robot token interface, and continuous control all at once.

01visual-language next token

Embodied reasoning

Molmo2 → Molmo2-ER

Specialize on 3.3M spatial and embodied examples, then rehearse with general VLM and instruction data.

02L LM

Robot pre-training

Molmo2-ER → MolmoAct2-Pretrain

Add setup, control, state, and FAST action tokens so the VLM becomes an autoregressive robot policy.

03L LM + L flow

Action post-training

Attach the action expert

Connect the DiT expert through per-layer KV conditioning and learn continuous trajectories on mixed robot data.

04robot-only adaptation

Embodiment fine-tuning

Adapt to one robot

Tune the same architecture for a target setup such as Franka, SO-100/101, bimanual YAM, or LIBERO.

token bridge

FAST makes continuous motion legible to the VLM

The action tokenizer is a training scaffold. The deployed continuous controller is still the flow-matching expert.

Input

1 second of robot motion

Mixed embodiments, rates, and control spaces

Normalize

1st to 99th percentiles

Pad

Shared 32-D action space

Transform

Frequency-domain coefficients

Quantize + BPE

2,048 action-token vocabulary

State tokenizer

Current robot values use simple normalization and 256 uniform bins. These tokens go in the prompt.

different jobs

FAST action tokenizer

Future motion is compressed into action tokens used as prediction targets. The expert never reads the target span.

MolmoAct2-FAST was trained on one million action sequences spanning absolute joint and delta end-effector control. For the mechanics behind frequency-space tokenization, see the separate FAST note.

molmoact2-think

Spend depth reasoning only where the scene changed

A cached depth buffer preserves static geometry while dynamic regions receive fresh depth-token predictions.

Current frame

changed regionstatic region

Adaptive depth router

Re-predict VQ-VAE depth codes for changed cells.
Replay cached codes for everything else.

Updated depth context

[cached depth] + [new depth]

Geometry-aware KV states

Continuous action expert

The paper reports a 17% latency reduction versus predicting dense depth tokens at every frame.

evidence

Designed for the deployment constraints that usually get skipped

The evaluation spans embodied reasoning, simulation, real-world zero-shot control, and adaptation.

63.8

Molmo2-ER average

Across 13 embodied-reasoning benchmarks

180 ms

Base action call

LIBERO on one NVIDIA H100

87.1%

Zero-shot Franka

Average success across real-world tasks

98.1%

LIBERO with Think

Average success after post-training

The remaining constraint is important: MolmoAct2 executes chunks of 10 to 30 actions before observing again. It cannot react inside a chunk, and out-of-the-box support is limited to heavily trained embodiments.

one-line summary

MolmoAct2 teaches a spatial VLM to speak robot motion with discrete tokens, then lets a flow-matching expert read the VLM's layer-by-layer attention state and turn noise into continuous control.

The mental model

MolmoAct2 starts by making the perception backbone more useful for robotics. Molmo2-ER is trained to reason about pointing, metric space, motion, camera viewpoints, and the agent's own frame of reference. The specialize-then-rehearse recipe adds those embodied skills without discarding the general visual and language ability inherited from Molmo2.

Robot pre-training then turns that spatial VLM into a discrete action policy. Current state values become simple state tokens, while one second of future motion is compressed by the open MolmoAct2-FAST tokenizer. Predicting those action tokens is not the final control interface. It is the scaffold that makes the VLM's internal attention state carry information about what the robot should do next.

Post-training attaches a DiT-style expert for continuous control. Every expert layer cross-attends to the keys and values from its matching VLM layer, so it can use grounded scene and task context while learning to transform noise into a smooth trajectory. The target action tokens are hidden from this path, and the flow loss is insulated from the VLM during post-training. MolmoAct2-Think adds explicit depth reasoning, but only regenerates depth codes for regions that changed since the previous frame.

Sources

Built by Suveen.

www.suveenellawela.com v.2026.5