Models

A preprint with MIT authors says Qwen3.8-27B-PEAR, trained only in simulation, completed 18 of 30 trials on a real dual-arm robot it never trained on, while the base model completed none

A preprint says a 27B model trained only in simulation completed 18 of 30 real-robot trials; its base model completed none. The tests covered two task types.

By ·

A preprint dated November 13, 2026, with authors from MIT, UC Berkeley, UCSD, Nvidia and Inco AI, reports that an open-weight 27-billion-parameter reasoning model learned to control real robots after training only in simulation. The training system is called PEAR, for Post-training Engine for Agentic Robotics, and the resulting model is Qwen3.8-27B-PEAR. On a dual-arm YAM robot that no model was trained on, the final model succeeded in 18 of 30 trials. These are trials of a small task set, not 30 different tests.

The essentials

Trials, not 30 different tests

The headline figure counts attempts at two task families, pickup and block alignment, on one robot. It shows transfer from simulation to a new robot within those families. It does not show that the model can do 30 different jobs, and the paper’s two prompted reasoning demos are not scored.

What the authors flag as limits

The paper reports no component ablations, one base model, two simulators and a small task set. Results depend on the prompt and on the controller reaching the target poses. Reasoning is slow, about 4.3 seconds per high-effort round. The authors also say the model needs the robot and its coordinate directions described in the prompt.

What is not established

Summary table

Summary table
PointWhat is stated as of November 7, 2026Source
PaperPreprint of November 13, 2026, arXiv 2611.18562arXiv
ModelQwen3.8-27B post-trained with PEAR by reinforcement learningarXiv
Training dataSimulation only, no demonstrations, no real-robot dataArXivSignals
Real robotDual-arm YAM, unseen in training; 30 trialsArXivSignals
ResultsFinal 18/30, LIBERO-only 7/30, base 0/30Sam on AI

FAQ

Is PEAR a model or a method?

PEAR is the training system. The model it produces is called Qwen3.8-27B-PEAR.

Did it pass 18 of 30 different tests?

No. It succeeded in 18 of 30 trials across two task families, pickup and block alignment.

Was any real-robot data used?

The paper says no. Training used simulation only, without demonstrations.

Method and limits

Checked on November 16, 2026. We read the arXiv paper and two summaries through search excerpts; one direct fetch of the paper was rate-limited. The request said ‘18 of 30 tests’; the paper counts trials on two task families. Affiliations come from the arXiv PDF excerpt; one summary page lists only lab tags.

Sources

Spotted an error in this article? Report it · Our corrections policy

OrigoTech logo

New: the app iPhone & iPad

OrigoTech is now an iPhone and iPad app

Read the articles natively, with “New” markers on unread ones, local search and offline reading of what you have already loaded. Free, no account, iOS 17 or later; ads appear between articles.

Rekha icon: a house drawn in a single stroke

From the same author Self-promotion

An Eulerian path, drawn with your finger

Rekha, the iPhone game by OrigoTech's author: connect every dot in a single stroke without tracing the same link twice, across 500 drawings that are all solvable.

The OrigoTech newsletter

A sourced weekly digest of AI tool news.

Read next

Models

Gemini 4 Hydrogen: price, benchmarks and Antigravity's new Orchestrator; Claude Code adds Code Mode, Codex CLI 0.168.0

Google released Gemini 4 Hydrogen on November 12, a fast model for everyday coding and agents at $1.50/$7.50 per million tokens, with a free API tier and a new Orchestrator in Antigravity that pairs it with Carbon or Argon. Also: Code Mode in Claude Code 2.1.323, Codex CLI 0.168.0, the agent-built AWS Emulator and Nebius's $40-45 billion capex plan for 2027.

· 5 min read