Research map / Multi-agent systems and games / LLM agents
Verifiable Machine Ethics in Changing Contexts
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use guarded context specifications to update ethical encodings during the reasoning cycle | JUNO with HERA · Smart-home case study | context-specific ethical reasoning | Helped |
| Apply model checking to the context-sensitive ethical agent | Utilitarian and Kantian JUNO agents · Smart-home fire scenario | fire-evacuation property verification | Helped |
| Use Kantian reasoning to veto actions that use a person as a means to an end | Kantian JUNO agent · Smart-home games-console scenario | games-console action selection | Mixed |
Closest papers by meaning
- Contextual Integrity in LLMs via Reasoning and Reinforcement Learning (NeurIPS 2025 · similarity 0.84)
- Towards Trustworthy Autonomous Systems via Conversations and Explanations (AAAI 2024 · similarity 0.81)
- MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning (AAAI 2026 · similarity 0.81)
- ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning (ICML 2025 · similarity 0.81)
- MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems (ICML 2026 · similarity 0.81)
- Towards a Theory of AI Personhood (AAAI 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.