Safety

Papers

• AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security (2026)
  Dongrui Liu et al.
  14.78
• AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration (2026)
  Jiaqi Liu et al.
  13.52
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security (2026)
  Dongrui Liu et al.
  12.12
• It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs (2026)
  Sangwoo Park et al.
  11.64
• Prompt Injection Attacks in Large Language Models and AI Agent Systems: A Comprehensive Review of Vulnerabilities, Attack Vectors, and Defense Mechanisms (2026)
  Saidakhror Gulyamov et al.
  10.60
• NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation (2026)
  NVIDIA et al.
  10.48
• From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors (2026)
  Jiejun Tan et al.
  10.15
• RedAct: Redacting Agent Capability Traces for Procedural Skill Protection (2026)
  Shuwen Xu et al.
  9.48
• SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning (2025)
  Edward Y. Chang et al.
  9.36
• OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration (2026)
  Xinchen Zhang et al.
  9.28
• Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows (2026)
  Harshada Badave et al.
  8.80
• A Survey on Agent Workflow -- Status and Future (2025)
  Chaojia Yu et al.
  8.10
• BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search (2026)
  Shiyu Liu et al.
  7.94
• PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models (2026)
  Ziliang Zhao et al.
  7.79
• Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments (2026)
  Yuxin Chen et al.
  7.79
• Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion (2026)
  Stine Lyngs{\o} Beltoft et al.
  7.31
• Evaluating routing stability and coordination in swarm-based multi-agent task-oriented dialogue systems (2026)
  Abuzar Khan et al.
  7.24
• Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing (2025)
  Jinwei Hu et al.
  6.91
• Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents (2026)
  Yingqi Zhang
  6.75
• The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? (2026)
  Xinyu Lu et al.
  6.75
• VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots (2025)
  Danil S. Grigorev et al.
  6.69
• Agentic Uncertainty Quantification (2026)
  Jiaxin Zhang et al.
  6.67
• Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents (2026)
  Xiang Liu et al.
  6.46
• Safety Aware Task Planning Via Large Language Models In Robotics (2025)
  Azal Ahmad Khan, Michael Andrev, Muhammad Ali Murtaza, et al.
  6.39
• Decentralized Safe Multi-agent Stochastic Optimal Control Using Deep Fbsdes And ADMM (2022)
  Marcus A. Pereira, Augustinos D. Saravanos, Oswin So, et al.
  6.34
• Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS (2025)
  Bingyu Yan et al.
  6.23
• Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults (2026)
  Rana Muhammad Usman
  5.88
• Generating Safe Autonomous Decision-making In ROS (2022)
  Yi Yang, Tom Holvoet
  5.84
• ProofAgent Harness: Open Infrastructure for Adversarial Evaluation of AI Agents (2026)
  Fouad Bousetouane
  5.82
• LACUNA: Safe Agents as Recursive Program Holes (2026)
  Yaoyu Zhao et al.
  5.82
• Open Challenges In Multi-agent Security: Towards Secure Systems Of Interacting AI Agents (2026)
  Christian Schroeder de Witt, Klaudia Krawiecka, Igor Krawczuk, et al.
  5.58
• From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents (2026)
  Laksh Advani
  5.49
• Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation (2026)
  Wei-Chen Li et al.
  5.49
• From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails (2026)
  Yuguang Zhou et al.
  5.49
• SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model (2026)
  Xiaoxin Lu et al.
  5.49
• Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents (2026)
  Yujun Zhou et al.
  5.46
• Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework (2026)
  Chingkwun Lam et al.
  5.41
• Distributionally Robust Free Energy Principle for Decision-Making (2025)
  Allahkaram Shafiei et al.
  5.29
• Existing LLMs Are Not Self-Consistent For Simple Tasks (2025)
  Zhenru Lin et al.
  5.04
• Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification (2026)
  Thanh Luong Tuan et al.
  5.01
• Provably Auditable and Safe LLM Agents from Human-Authored Ontologies (2026)
  Aaron Sterling
  5.01
• Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming (2026)
  Nicholas Saban
  5.01
• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents (2026)
  Yunhao Yang et al.
  5.01
• CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs (2026)
  Mohammad Akyash et al.
  5.01
• Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems (2026)
  Yingzhuo Liu
  5.01
• Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations (2026)
  Salvatore Greco et al.
  5.01
• Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version) (2026)
  Christopher J. Wedge et al.
  5.01
• Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies (2026)
  Christian Llanes et al.
  5.01
• Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation (2026)
  Yuchen Ling et al.
  5.01
• SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems (2026)
  Tarun Sharma
  5.01