AI ethics evidence index Search
Source-linked daily record
Evidence record 7502 · automatically gathered

SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM

In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environmental variation. We propose SAIL, a framework that reframes robot imitation as an iterative refinement problem capable of scaling with test-time compute. SAIL utilizes Monte Carlo Tree Search, where each node is a complete trajectory and edges correspond to trajectory refinements. The process is guided by three core components: an automated archive o

Record details

Published: 9 March 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Agents & autonomy · Shared topic: Environment

Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams

arXiv · 9 March 2026

Shared topic: Agents & autonomy · Shared topic: Environment

SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation

arXiv · 9 March 2026

Shared topic: Agents & autonomy · Shared topic: Environment

AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents

arXiv · 10 March 2026

Shared topic: Agents & autonomy · Shared topic: Environment

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

arXiv · 8 March 2026

Shared topic: Agents & autonomy · Shared topic: Environment

CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents

arXiv · 11 March 2026

Shared topic: Agents & autonomy · Shared topic: Environment

Distributed Legal Infrastructure for a Trustworthy Agentic Web

arXiv · 6 March 2026

How to cite this record

ethics.ai (9 March 2026), “SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM,” evidence record 7502, https://ethics.ai/record/7502 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.