Robotics · arXiv:2611.01112 v1 · submitted 31 Oct 2026
Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation
The paper says
“We present Auriga, a task-agnostic agent harness that closes 68.3% of this gap in zero-shot manipulation without target-task trials or resets.”
from the abstract · picked out as the main claim by a classifier
Reviews
Reviews by people
No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies. On RoboDojo, a large planning-execution gap separates high-level task decisions from physical execution: removing arm execution raises GPT-6 Astra's success rate from 22.5% under the reference control interface to 76.2%. We present Auriga, a task-agnostic agent harness that closes 68.3% of this gap in zero-shot manipulation without target-task trials or resets. In Auriga, the model makes all task decisions over an explicit task belief and acts through either direct tool calls or synthesized multi-step Python programs, while the harness supplies calibrated 3D measurements, finger-referenced dual-arm control, and a single admission gateway to the robot. Before motion, the model inspects a visual trajectory preview while simulation is paused; during execution, the harness checks declared stage tolerances and grasp bounds, stopping the robot on divergence and returning the measured discrepancy for in-place recovery. Developed across 13 cross-task capability iterations and frozen for evaluation, Auriga ranks first on the RoboDojo leaderboard with a 57.7% success rate (64.0 Score), more than doubling the reference harness on the same model, and remains first under scene randomization while learned policies drop by up to 33.9%. On RoboCasa365, the same frozen harness reaches a 73.2% success rate, outperforming VLA-assisted agents by up to 23.1% on composite tasks. Project page: https://auriga.stelledge.com/ Code: https://github.com/lose4578/Auriga
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-03 · no language-model review
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.12 · states limitation 0.19 · human participants 0.04 · controlled comparison 0.97 · randomized assignment 0.08 · states quantitative result 0.99 · compares with prior results 0.98 · mentions code or data availability 0.97
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies. | background 0.96 | 0.09 | 0.04 | asserted 0.99 |
| On RoboDojo, a large planning-execution gap separates high-level task decisions from physical execution: removing arm execution raises GPT-6 Astra's success rate from 22.5% under the reference control interface to 76.2%. | gap 0.50 | 0.81 | 0.06 | asserted 1.00 |
| We present Auriga, a task-agnostic agent harness that closes 68.3% of this gap in zero-shot manipulation without target-task trials or resets. | contribution 0.96 | 0.95 | 0.78 | asserted 1.00 |
| In Auriga, the model makes all task decisions over an explicit task belief and acts through either direct tool calls or synthesized multi-step Python programs, while the harness supplies calibrated 3D measurements, finger-referenced dual-arm control, and a single admission gateway to the robot. | method 0.96 | 0.86 | 0.09 | asserted 1.00 |
| Before motion, the model inspects a visual trajectory preview while simulation is paused; during execution, the harness checks declared stage tolerances and grasp bounds, stopping the robot on divergence and returning the measured discrepancy for in-place recovery. | method 1.00 | 0.86 | 0.04 | asserted 1.00 |
| Developed across 13 cross-task capability iterations and frozen for evaluation, Auriga ranks first on the RoboDojo leaderboard with a 57.7% success rate (64.0 Score), more than doubling the reference harness on the same model, and remains first under scene randomization while learned policies drop by up to 33.9%. | result 1.00 | 0.96 | 0.34 | asserted 1.00 |
| On RoboCasa365, the same frozen harness reaches a 73.2% success rate, outperforming VLA-assisted agents by up to 23.1% on composite tasks. | result 1.00 | 0.94 | 0.11 | asserted 1.00 |
| Project page: https://auriga.stelledge.com/ Code: https://github.com/lose4578/Auriga | contribution 0.53 | 0.20 | 0.02 | unclear 0.96 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.97
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-03: 1 request, 6,576 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Cited by 2 Pith papers
Reviewed papers on Pith that cite this one. The full citation record
- ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models cs.RO · Nov 2026
- Embodied First Exam cs.RO · Nov 2026
Challenges and discussion
Know something about this paper? Leave a comment.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment