… The following papers were recommended by the Semantic Scholar API SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces 2026 VESTA: A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents 2026 Plant, Persist, Trigger: Sleeper Attack … …
… The following papers were recommended by the Semantic Scholar API Orchard: An Open-Source Agentic Modeling Framework 2026 Auditing Agent Harness Safety 2026 SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety 2026 Security Risks in Tool-Enabled AI Agents: A Systematic Analysis … …
… The following papers were recommended by the Semantic Scholar API The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents 2026 Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents 2026 AIRGuard: Guarding Agent Actions wit… …
… Compared with strong baselines, FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%. These results suggest that failed trajectories can provide structured repair supervision for safer self-evolving agents. …
… The following papers were recommended by the Semantic Scholar API STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems 2026 PolicyBank: Evolving Policy Understanding for LLM Agents 2026 On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment… …
… The following papers were recommended by the Semantic Scholar API AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations 2026 HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools 2026 TwinRouterBench: Fast Static and Live Dynamic Eval… …
Papers arxiv:2605.06652 When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels Published on May 7 Submitted by Sushant Gautam on May 8 Simula Metropolitan Center for Digital Engineering SimulaMet Authors: Sushant Gautam , , , , , , , , Abstract Comparative s… …
… Rethinking Safety Evaluation for Phone-Use Agents Published on May 8 Submitted by Zhengyang Tang on May 12 Authors: Zhengyang Tang , , , , , , , , , , , , , , , , Zheng Ruan , , , , Abstract PhoneSafety benchmark reveals that avoiding harmful outcomes doesn't necessarily indicate safety, as models … …
Papers arxiv:2605.31170 Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion Published on May 29 Submitted by Federico Torrielli on Jun 1 AI Safety & Interpretability Lab Authors: , William Brach , Federico Torrielli , , , , , Lukas Galke Poech Abst… …
… AI-generated summary Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent behavior. …