RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation. Existing alignment methods often rely on coarse refusal signals or static supervision, making it difficult to balance safety with useful tool execution across diverse agentic risks. We introduce RUBAS, a rubric-based reinforcement learning framework for agent safety. RUBAS decomposes agent behavior into four dimensions: tool-use safety,
Record details
Published: 2 June 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Agents & autonomy
Retrieved: 14 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.
Agentic Safety is an Epistemic Property, Not a Behavioral One
arXiv · 2 June 2026
MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data
arXiv · 1 June 2026
MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation
arXiv · 1 June 2026
RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents
arXiv · 1 June 2026
ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment
arXiv · 31 May 2026
From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents
arXiv · 4 June 2026
How to cite this record
ethics.ai (2 June 2026), “RUBAS: Rubric-Based Reinforcement Learning for Agent Safety,” evidence record 3228, https://ethics.ai/record/3228 (originally published by arXiv).
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.