FlowingFlowing
← Back to all development cases
Development case · blind model judgment pending independent human review; not a formal Benchmark conclusion.
AutocompleteWith cards better143 / 162 · 15c3f447ed9f9bb8

A Survey on Improving Human Robot Collaboration through Vision-and-Language Navigation

Psychology and cognitive neuroscience · 2512.00027v1

FLOWING EVIDENCE BENCHMARK

How do we tell whether Evidence helps?

At the same writing position, with the same model and task, how does supplying retrieved paper passages change the first output? We compare matched versions and retain ties, unusable outputs and incomplete reviews.

SAME DRAFT · EVIDENCE ON OR OFF

01 · FIXED WRITING POSITION

MANUSCRIPT

Same writing position ▌

Matched autocomplete at the same draft position

02 · TWO MATCHED INPUTS

SHARED BY BOTH

Manuscript context, model, task and prompt

A · With Evidence

Retrieved paper passages supplied

B · Without Evidence

No retrieved passages supplied

LLM

Same model and version

A → first output

B → first output

Blind judge agent

First outputs are anonymized as X and Y

Continuation review: accuracy, fit to the writing task and usability
Returns: X preferred / tie / Y preferred / both unusable

Order check: X / Y → Y / X

HOW DOES BLIND JUDGING WORK?

① Anonymize both outputs
The judge sees the same draft and both first outputs without knowing which received Evidence.

② Compare and swap order
The judge applies task-specific criteria in X/Y and then Y/X order.

③ Review disagreements
A third pass resolves disagreements. Incomplete reviews remain in the denominator.

How are positions and cards selected?

The evaluation uses seven fields with forty fixed ordinary autocomplete positions in each, for 280 total. A position does not need to require a literature citation in its next sentence. Each Flowing request receives three to five retrieved cards: five when all pass the relevance gate, without padding with weak cards. The run supplied 1,355 cards: 244 positions received five, 27 received four, and nine received three.

ADOPTION · 150/280

Adoption coverage

After drafting, the model returns an evidenceUse array identifying cards that materially affected facts, correction, direction, scope, terminology, or expression. A nonempty array counts as adoption.

OUTCOMES · 70 / 7 / 30

Full outcomes after adoption

Paired outcomes are counted only when the model reports adoption and both arms produce text. Among 107 comparable positions, Flowing was preferred in 70, 7 tied, and no-Evidence was preferred in 30; one tie was unusable in both arms.

How are the two table percentages calculated?

ADOPTION COVERAGE

150adopted
÷
280all positions
=
54%

FLOWING PREFERENCE AFTER ADOPTION

70Flowing preferred
÷
107comparable adopted positions
=
65%

evidenceUse is the model’s structured report of its own generation process. It does not require a citation and is not rejected merely because a faithful source paraphrase is not verbatim. Actual manuscript citations continue to use separate strict source verification. The previous 140-position result remains retained for traceability.

These are development-stage model-reported adoption and blind-judge results pending independent human review. They are not formal Benchmark conclusions and do not, on their own, establish causality.

Manuscript writing position

Text excerpt · not a PDF page

Research manuscript · excerpt

A Survey on Improving Human Robot Collaboration through Vision-and-Language Navigation

1. INTRODUCTION

…orough resource that inspires further research at the intersection of VLN and robotics. We advocate that the future VLN systems should support proactive clarification, real-time feedback, and contextual reasoning through advanced natural language understanding (NLU) techniques. Additionally, decentralized decision-making frameworks with dynamic role assignment are essential for scalable, efficient multi-robot collaboration. These innovations can significantly enhance human-robot interaction (HRI) and enable real-world deployment in domains such as healthcare, logistics, and disaster response.

…D environments ( Anderson et al., 2018b ) ( Chen et al., 2019 ) , ( Thomason et al., 2020 ) , . In VLN tasks, agents interpret human instructions and leverage visual observations to traverse previously unseen spaces with increasing reliability. These agents integrate visual inputs and language instructions to generate navigation commands, provide verbal feedback, execute manipulation actions, and identify object locations ( Wu et al., 2023 ) . As a hallmark of embodied AI (EAI) ( Das et al., 2018 ) , VLN has catalyzed extensions into vision-language-guided manipulation and outdoor navigation.

↓ Next paragraph was generated here

The highlighted text is near the writing position. This is a layout of the evaluation input, not a PDF screenshot.

A matched comparison at the same writing positionJudgment: With cards better

Both arms use the same model, task and manuscript context. Only the retrieved passages differ. The first recorded output from each arm is shown below.

Evidence

Same model and position · retrieved passages supplied · first output

Preferred by blind review

A key methodological shift in this trajectory was the move from graph-based navigation, in which agents traverse a pre-prepared navigation graph, to Vision-Language Navigation in Continuous Environments (VLN-CE), which removes the need for such graphs and allows agents to move freely in 3D spaces. This continuous formulation has been adopted because it better reflects realistic robotic navigation and permits agents to respond effectively to verbal commands.

Passages supplied to the Evidence version

Cog-GA: A Large Language Models-based Generative Agent for Vision-Language Navigation in Continuous Environments

Vision Language Navigation (VLN) plays a pivotal role in robotics, where an embodied agent carries out natural language instructions inside real 3D environments based on visual observations. Traditionally, the movements of agents in VLN environments are processed by a pre-prepared navigation graph t…

Read full passage excerpt

Vision Language Navigation (VLN) plays a pivotal role in robotics, where an embodied agent carries out natural language instructions inside real 3D environments based on visual observations. Traditionally, the movements of agents in VLN environments are processed by a pre-prepared navigation graph that the agent traverses. Recognizing this, Krantz et al. [ 15 ] introduced an alternative approach known as Vision-Language Navigation in Continuous Environments (VLN-CE). Unlike traditional methods, VLN-CE eliminates the need for navigation graphs, enabling agents to move freely in 3D spaces. This framework has gained prominence for its realistic and adaptable approach to robotic navigation, allowing agents to respond effectively to verbal commands.

Model-reported card use

The model did not report that any card materially affected this completion.

No Evidence

Same model and position · no retrieved passages · first output

Not preferred in this comparison

No continuation text was produced.

Model action：complete

Result of this comparison

The blinded model review preferred the Evidence version. Its original rationale appears below.

Read the original model judgment

Output A is empty, providing no paragraph continuation despite the task requiring content. Output B provides a coherent academic paragraph that directly draws from the supplied source about VLN-CE, accurately describing the shift from graph-based navigation to continuous environments, the elimination of navigation graphs, and the benefits for realistic robotic navigation and verbal command response. The content is well-grounded in the source snippet, maintains the academic tone of the draft, and creates a logical bridge between the draft's discussion of VLN and the specific methodological evolution to continuous environments.

The passages are input material; their presence does not mean an output used them or that they support every claim. Draft and source passages are excerpted; no simulated scores or PDF appear here.