Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-11
Code: https://github.com/ikus060/rdiffweb
Sources
- CoACT: Action-Preserving Observation Compression for Coding Agents
- ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
- LlamaFirewall: An open source guardrail system for building secure AI agents
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- The Llama 3 Herd of Models
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Kimi K3: Open Frontier Intelligence
- ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
- SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
- DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
- AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- Decoupled Weight Decay Regularization
- gpt-oss-120b & gpt-oss-20b Model Card
- ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction
- SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants
- Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents
- HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark
- S cubed: Improving Agent Safety through Multi-Stage Defense
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems