Paper Detail

$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning

Lehong Wu, Yuxiao Qu, Zheyuan Hu, Ivan Zhang, Limin Wei, Zackory Erickson, Aviral Kumar

arxiv Score 14.3

Published 2026-08-26 · First seen 2026-08-27

General AI

Abstract

Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whether this mechanism can improve robotic manipulation remains unclear, where long-horizon tasks require tracking partial progress, reasoning about object relations, recovering from mistakes, and steering noisy low-level policies. In this paper, we study whether VLMs can be trained to reason directly in natural language to guide low-level manipulation policies. We introduce $R^3$, a simple post-training recipe that turns off-the-shelf VLMs into robotic reasoners: it first mid-trains a VLM on expert-generated reasoning traces to initialize the desired reasoning style, then improves the reasoner with single-step rubric-based RL from offline action data. Unlike prior robotic reasoning methods that mostly use structured traces as auxiliary supervision, $R^3$ trains free-form language reasoning to produce test-time guidance for action. We instantiate $R^3$ on Language Table and simulated bimanual grocery packing, two controlled testbeds for studying robotic reasoning and long-horizon manipulation. $R^3$ improves exploration and generalization across unseen tasks and significantly outperforms instruction-only imitation learning baselines on both benchmarks. Our analyses suggest that free-form language reasoning can function as a test-time compute mechanism for steering low-level policies. Our project page is available at https://robotic-reasoner.github.io/.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{wu2026r,
  title = {\$R\textasciicircum{}3\$: Training Robots to Reason in Natural Language via Reinforcement Learning},
  author = {Lehong Wu and Yuxiao Qu and Zheyuan Hu and Ivan Zhang and Limin Wei and Zackory Erickson and Aviral Kumar},
  year = {2026},
  abstract = {Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whether this mechanism can improve robotic manipulation remains unclear, where long-horizon tasks require tracking partial progress, reasoning about object relations, recovering from mistakes, and steering noisy low-level policies. In this paper, we study whether VLMs can be trained to reason directly i},
  url = {https://arxiv.org/abs/2608.26053},
  keywords = {cs.RO, cs.AI, cs.CL, cs.LG},
  eprint = {2608.26053},
  archiveprefix = {arXiv},
}

Metadata

{}