ARC: A Reasoning Recipe for Robot Foundation Models

Gokul Puthumanaillam, Tao Sun, Elie Aljalbout, Moritz Reuss, Zhaoshuo Li, Fabio Ramos, Ankit Goyal, Jenai Xuning Yang · N/A · 2026

Summary

The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale.

Abstract Summary

The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale. We show that there exists an effective and efficient complementary approach: the right reasoning recipe can substantially improve the zero-shot task performance of existing state-of-the-art RFMs. We refer to this recipe as ARC. It consists of three key ingredients: a reasoning trace, a scalable automatic labeling pipeline, and a strategy for adapting pretrained RFMs to use these traces for control. First, we find that effective reasoning traces should be grounded in the robot's next action and explain its causal structure: why the action is appropriate and what effect it should produce. Second, we show that these traces can be generated automatically from existing demonstrations, enabling us to construct ARC-Trace-DROID from DROID without collecting new robot data. Third, we show how state-of-the-art VLAs such as $π_{0.5}$ and WAMs such as Cosmos3-Nano-Policy can learn to use these traces for control, with fine-tuning and inference tailored to each model's architecture and capabilities. Using ARC, we obtain gains in zero-shot RFM performance that, to our knowledge, are unprecedented without additional robot demonstrations or foundation-scale training. The adapted models establish a new state of the art on RoboLab-120 and MolmoSpaces, with gains of up to 50 percentage points on RoboLab-Reasoning-50. On real robots, ARC improves $π_{0.5}$'s task success by 82.2 percentage points. Project website: https://arc-robot-reasoning.github.io/

Key Points

The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale.
We show that there exists an effective and efficient complementary approach: the right reasoning recipe can substantially improve the zero-shot task performance of existing state-of-the-art RFMs.
We refer to this recipe as ARC
It consists of three key ingredients: a reasoning trace, a scalable automatic labeling pipeline, and a strategy for adapting pretrained RFMs to use these traces for control.
First, we find that effective reasoning traces should be grounded in the robot's next action and explain its causal structure: why the action is appropriate and what effect it should produce.

Preliminaries and Problem Statement

Robot task setting. We consider a robot operating in a partially observed environment. A task is specified by an instruction $g\in\mathcal{G}$. At time $t$, the robot receives an observation $o_{t}\in\mathcal{O}$ and executes an action $a_{t}$ $\in\mathcal{A}$.

We denote the interaction history by $h_{t}=(o_{0},a_{0},\ldots,a_{t-1},o_{t}).$ To cover models that predict several actions at once, we write $\mathbf{a}_{t}=(a_{t},\ldots,a_{t+H-1})$ for an action chunk of horizon $H$.

Preliminaries and Problem Statement — ARC: A Reasoning Recipe for Robot Foundation Models — Figure 1 : Overview of Arc : Arc -Trace automatically relabels DROID with action-grounded causal traces to produce Arc -Trace-DROID. We show how to fine-tune VLAs and WAMs with this supervision, achieving benchmark-leading performance without additional robot demonstrations.

The Arc Framework

We now describe the components of Arc : the reasoning representation (Sec. 4.1 ), the Arc -Trace relabeling pipeline (Sec. 4.2 ), and the fine-tuning recipe that connects reasoning to control (Sec. 4.3 ). We represent $r_{t}$ in natural language, reusing the model’s pretrained language conditioning.

We examine ECoT-style reasoning and semantic subtask supervision, adapting both formats to the same $\pi_{0.5}$ backbone and fine-tuning it with each ( Zawalski et al., 2024 ; Black et al., 2025a ) .

The Arc Framework — ARC: A Reasoning Recipe for Robot Foundation Models — Figure 2 : Reasoning traces and action-expert attention.

Experiments

We evaluate $\pi_{0.5}$+ Arc (VLA) and Cosmos3-Nano+ Arc (WAM) (both finetuned on Arc -Trace-DROID) zero-shot on RoboLab-120 ( Yang et al., 2026 ) , MolmoSpaces ( Kim et al., 2026 ) , and RoboLab-Reasoning-50. We additionally evaluate Arc -$\pi_{0.5}$ on paired real-world tasks without further fine-tuning. All simulation and hardware experiments use the DROID embodiment.

We use Qwen3.6-35B-A3B as the default external VLM (ablated in section 5.2 ). General task performance.

Experiments — ARC: A Reasoning Recipe for Robot Foundation Models — Figure 3 : Overview of the Arc -Trace relabeling pipeline, illustrated with an example task.

AI Use Statement

We used vision-language models to automatically generate action-grounded causal annotations for ARC-Trace and, during evaluation, to generate reasoning traces from task instructions and camera observations. The models and prompting procedures are described in the methodology and appendix. Large language models also assisted with manuscript drafting and editing.

The authors take responsibility for the final manuscript, reported results, and all AI-assisted content.

AI Use Statement — ARC: A Reasoning Recipe for Robot Foundation Models — Table 1 : RoboLab-120 benchmark results. SR is success rate; +values give gains over the corresponding base policy in p.p.

Reproducibility statement

We describe ARC’s reasoning representation and training objectives in Sections 4.1 and 4.3 . Appendix A.1 details the ARC-Trace construction pipeline and labeling prompts. Model-specific training configurations and hyperparameters are provided in Appendices B.1 and B.2 , while inference prompts and deployment procedures are documented in Appendices B.3 and B.3.1 .

The evaluation protocols, benchmark construction, baseline implementations, and hardware setup are described in Appendices C.1.3 , C.3 , and C.2 .

Reproducibility statement — ARC: A Reasoning Recipe for Robot Foundation Models — Table 2 : MolmoSpaces benchmark results.

Sources and Demonstrations

Figures are reproduced from Puthumanaillam et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.