Papers arxiv:2605.29801 AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Published on May 28 Submitted by Dongrui Liu on May 29 1 Paper of the day shanghai ailab Authors: , , , , Guanxu Chen , , , , , , , , , , , , , , , , Qihan Ren , Junxiao Yang Abstra… …
… Our construction pipeline rejects 70.3% of LLM -generated candidates at a search-based external-verification stage, calibrating how unreliable industrial QA remains after LLM -only filtering.Our evaluation decouples raw correctness, scored by a Qwen3-Max judge validated at κ w = 0.798 against a dom… …
… 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… …
… AI-generated summary The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. …
… The following papers were recommended by the Semantic Scholar API IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia 2026 ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models 2026 HarmChip: Evaluating Hardware Security Centri… …
Papers arxiv:2605.11882 On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment Published on May 12 Submitted by LIQIIIII on May 13 Authors: Bo Yin , Qi Li , Abstract FATE is an on-policy framework that uses failure trajectories to improve agent safety and performance through… …
… Automated Auditing of LLM Agent Benchmarks 2026 AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair 2026 ValueBlindBench: Agreement-Gated Stress Testing of LLM-Judged Investment Rationales Before Returns Are Observable 2026 JudgeSense: A Bench… …
… To demonstrate its reconfigurability, we apply MASCing to two different safety objectives and observe consistent gains with negligible overhead across seven open-source MoE models. …
… The following papers were recommended by the Semantic Scholar API Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning 2026 SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models 2026 Risk-Adjusted H… …
… The following papers were recommended by the Semantic Scholar API SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics 2026 ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming 2026 Transient Turn Injection: Exposing Stateless Multi-… …