Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents
AI agents encounter learning opportunities in every episode they run, and discard nearly all of them: the underlying models are frozen at deployment, so an agent that resolves a difficult request today starts from zero when it recurs tomorrow. Yet ordinary operation already produces feedback, in the form of outcome verdicts and after-the-fact corrections. We show that this feedback is a sufficient signal for continual learning when the frozen model is paired with an external memory that distils
Record details
Published: 24 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Jobs & economy · Agents & autonomy
Retrieved: 27 July 2026
Related evidence
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.
The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents
arXiv cs.AI · 24 July 2026
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
arXiv · 23 July 2026
Open Veins of Algorithmic Auditing: Why AI Assessment Lags Behind Its Deployment in the Global South
arXiv · 23 July 2026
Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic Manufacturing
arXiv cs.AI · 22 July 2026
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
arXiv · 21 July 2026
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
arXiv · 21 July 2026
How to cite this record
ethics.ai (24 July 2026), “Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents,” evidence record 13708, https://ethics.ai/record/13708 (originally published by arXiv cs.AI).
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.