PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Project page: https://qwenlm.github.io
Sources
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
- AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets
- A Safety and Security Framework for Real-World Agentic Systems
- Are Your Agents Upward Deceivers?
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Decoupled Weight Decay Regularization
- ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
- Kimi K2.5: Visual Agentic Intelligence
- SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
- Qwen3 Technical Report
- Qwen2.5 Technical Report
- RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks