{"total":108,"rows":[{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548,"area":"agents"},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2408.00989","title":"On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents","created":"2024-08-02","cited_by_count":99,"area":"agents"},{"id":"2405.05175","title":"AirGapAgent: Protecting Privacy-Conscious Conversational Agents","created":"2024-05-08","cited_by_count":94,"area":"agents"},{"id":"2502.08586","title":"Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks","created":"2025-02-12","cited_by_count":49,"area":"agents"},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47,"area":"agents"},{"id":"2410.01606","title":"Automated Red Teaming with GOAT: the Generative Offensive Agent Tester","created":"2024-10-02","cited_by_count":45,"area":"agents"},{"id":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2510.04885","title":"RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection","created":"2025-10-06","cited_by_count":36,"area":"agents"},{"id":"2411.03814","title":"MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue","created":"2024-11-06","cited_by_count":33,"area":"agents"},{"id":"2604.04989","title":"SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement","created":"2026-04-05","cited_by_count":30,"area":"agents"},{"id":"2312.14302","title":"Exploiting Novel GPT-4 APIs","created":"2023-12-21","cited_by_count":28,"area":"agents"},{"id":"2406.08689","title":"Security of AI Agents","created":"2024-06-12","cited_by_count":26,"area":"agents"},{"id":"2410.06215","title":"DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback","created":"2024-10-08","cited_by_count":25,"area":"agents"},{"id":"2602.11510","title":"AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems","created":"2026-02-12","cited_by_count":25,"area":"agents"},{"id":"2508.10880","title":"Searching for Privacy Risks in LLM Agents via Simulation","created":"2025-08-14","cited_by_count":22,"area":"agents"},{"id":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2310.00322","title":"Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games","created":"2023-09-30","cited_by_count":17,"area":"agents"},{"id":"2506.12152","title":"Because we have LLMs, we Can and Should Pursue Agentic Interpretability","created":"2025-06-13","cited_by_count":16,"area":"agents"},{"id":"2502.00757","title":"AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement","created":"2025-02-02","cited_by_count":14,"area":"agents"},{"id":"2601.04583","title":"Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries","created":"2026-01-08","cited_by_count":13,"area":"agents"},{"id":"2507.05445","title":"A Systematization of Security Vulnerabilities in Computer Use Agents","created":"2025-07-07","cited_by_count":11,"area":"agents"},{"id":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2402.08078","title":"Large Language Models as Agents in Two-Player Games","created":"2024-02-12","cited_by_count":10,"area":"agents"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2602.13477","title":"OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage","created":"2026-02-13","cited_by_count":9,"area":"agents"},{"id":"2606.22528","title":"Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents","created":"2026-06-21","cited_by_count":8,"area":"agents"},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7,"area":"agents"},{"id":"2603.20320","title":"The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents","created":"2026-03-19","cited_by_count":7,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2603.22341","title":"T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search","created":"2026-03-21","cited_by_count":6,"area":"agents"},{"id":"2606.02540","title":"SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction","created":"2026-06-01","cited_by_count":6,"area":"agents"},{"id":"2507.11299","title":"Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian","created":"2025-07-15","cited_by_count":5,"area":"agents"},{"id":"2601.13518","title":"AgenticRed: Evolving Agentic Systems for Red-Teaming","created":"2026-01-20","cited_by_count":5,"area":"agents"},{"id":"2604.08608","title":"Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines","created":"2026-04-08","cited_by_count":5,"area":"agents"},{"id":"2604.20911","title":"Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents","created":"2026-04-22","cited_by_count":5,"area":"agents"},{"id":"2507.00914","title":"Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications","created":"2025-07-01","cited_by_count":4,"area":"agents"},{"id":"2605.09278","title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","created":"2026-05-10","cited_by_count":4,"area":"agents"},{"id":"2605.24134","title":"ProofAgent Harness: Open Infrastructure for Adversarial Evaluation of AI Agents","created":"2026-05-22","cited_by_count":4,"area":"agents"},{"id":"2605.30322","title":"Gram: Assessing sabotage propensities via automated alignment auditing","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2606.16871","title":"Human-on-the-Bridge: Scalable Evaluation for AI Agents","created":"2026-06-15","cited_by_count":4,"area":"agents"},{"id":"2502.12630","title":"Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach","created":"2025-02-18","cited_by_count":3,"area":"agents"},{"id":"2601.22569","title":"Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2602.09947","title":"Trustworthy Agentic AI Requires Deterministic Architectural Boundaries","created":"2026-02-10","cited_by_count":3,"area":"agents"},{"id":"2602.21806","title":"Where Agent Frameworks Fall Short: Examining Functional Challenges and Usability Concerns","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2604.08465","title":"From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis","created":"2026-04-09","cited_by_count":3,"area":"agents"},{"id":"2605.17986","title":"LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection","created":"2026-05-18","cited_by_count":3,"area":"agents"},{"id":"2505.14215","title":"Safety Degradation in AI Agents","created":"2025-05-20","cited_by_count":2,"area":"agents"},{"id":"2512.08104","title":"AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2603.09134","title":"AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations","created":"2026-03-10","cited_by_count":2,"area":"agents"},{"id":"2604.22871","title":"AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models","created":"2026-04-23","cited_by_count":2,"area":"agents"},{"id":"2605.02463","title":"When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2606.18356","title":"SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2606.22329","title":"BabelJudge: Measuring LLM-as-a-Judge Reliability Across Languages and Agent Trajectories","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2608.08160","title":"Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives","created":"2026-08-08","cited_by_count":2,"area":"agents"},{"id":"2609.07529","title":"CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement","created":"2026-09-07","cited_by_count":2,"area":"agents"},{"id":"2503.17753","title":"Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information","created":"2025-03-22","cited_by_count":1,"area":"agents"},{"id":"2510.13857","title":"From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering","created":"2025-10-12","cited_by_count":1,"area":"agents"},{"id":"2512.08139","title":"Robust Agents in Open-Ended Worlds","created":"2025-12-09","cited_by_count":1,"area":"agents"},{"id":"2512.19016","title":"DREAM: Dynamic Red-teaming across Environments for AI Models","created":"2025-12-22","cited_by_count":1,"area":"agents"},{"id":"2601.14660","title":"NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents","created":"2026-01-21","cited_by_count":1,"area":"agents"},{"id":"2602.02395","title":"David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning","created":"2026-02-02","cited_by_count":1,"area":"agents"},{"id":"2602.07391","title":"NAAMSE: Framework for Evolutionary Security Evaluation of Agents","created":"2026-02-07","cited_by_count":1,"area":"agents"},{"id":"2603.13325","title":"Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2603.20925","title":"Profit is the Red Team: Stress-Testing Agents in Strategic Economic Interactions","created":"2026-03-21","cited_by_count":1,"area":"agents"},{"id":"2604.22879","title":"Beyond Single-Agent Alignment: Preventing Context-Fragmented Violations in Multi-Agent Systems","created":"2026-04-24","cited_by_count":1,"area":"agents"},{"id":"2604.22971","title":"Peer Identity Bias in Multi-Agent LLM Evaluation: An Empirical Study Using the TRUST Democratic Discourse Analysis Pipeline","created":"2026-04-24","cited_by_count":1,"area":"agents"},{"id":"2605.04019","title":"Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours","created":"2026-05-05","cited_by_count":1,"area":"agents"},{"id":"2605.08382","title":"SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2605.09027","title":"GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2605.27766","title":"Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2605.28122","title":"SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents","created":"2026-05-27","cited_by_count":1,"area":"agents"},{"id":"2606.04037","title":"Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2607.25379","title":"Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2508.19500","title":"Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills","created":"2025-08-27","cited_by_count":0,"area":"agents"},{"id":"2509.06701","title":"Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks","created":"2025-09-08","cited_by_count":0,"area":"agents"},{"id":"2510.25941","title":"RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline","created":"2025-10-29","cited_by_count":0,"area":"agents"},{"id":"2602.04487","title":"The Supportiveness-Safety Tradeoff in LLM Well-Being Agents","created":"2026-02-04","cited_by_count":0,"area":"agents"},{"id":"2603.00121","title":"Graph-theoretic Agreement Framework for Multi-agent LLM Systems","created":"2026-02-23","cited_by_count":0,"area":"agents"},{"id":"2604.01039","title":"Evaluation and Hardening of LLM System Instructions Against Extraction via Encoding Attacks","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2604.23483","title":"Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines","created":"2026-04-26","cited_by_count":0,"area":"agents"},{"id":"2605.19915","title":"LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions","created":"2026-05-19","cited_by_count":0,"area":"agents"},{"id":"2605.28098","title":"Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.08531","title":"ForesightSafety-SAGE:A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents","created":"2026-06-07","cited_by_count":0,"area":"agents"},{"id":"2606.10747","title":"The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2606.14831","title":"Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2606.17092","title":"Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2606.23927","title":"RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems","created":"2026-06-22","cited_by_count":0,"area":"agents"},{"id":"2606.24245","title":"AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2608.02553","title":"A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.04018","title":"Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Teaming","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2608.08164","title":"STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2608.09485","title":"Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.11207","title":"Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2608.16806","title":"Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.21377","title":"Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2608.23763","title":"TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.27439","title":"RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution","created":"2026-08-27","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}