Cumulative and Audited Guardrail Tool Evolution for LLM Agent Safety
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/openclaw/openclaw
Terminology
Sources
- A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents
- A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
- A Language Agent for Autonomous Driving
- SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
- Agent-SafetyBench: Evaluating the Safety of LLM Agents
- GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
- A Survey on Agentic Security: Applications, Threats and Defenses
- AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- DeepSeek-V3 Technical Report
- GPT-4 Technical Report
- Constitutional AI: Harmlessness from AI Feedback
- Gemini: A Family of Highly Capable Multimodal Models
- AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
- AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
- MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
- How Secure is Code Generated by ChatGPT?
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents