conftrace_

agent safety

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) llm agent (2) agent system (2) ai safety (2) threat model (1) multi-agent system (1) adversarial generation (1) sycophancy detection (1) prompt refinement (1) tool access (1)

Papers

Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents EACL 2026 SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator ACL 2026 AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ICLR 2025 Agent vs. Agent: Automated Data Generation and Red-Teaming for Custom Agentic Workflows EMNLP 2025 Aligned LLMs Are Not Aligned Browser Agents ICLR 2025 Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation ACL 2025 Effective Red-Teaming of Policy-Adherent Agents EMNLP 2025 OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research JMLR 2024