{"list":"other","total":61,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138},{"id":"2006.14580","title":"Backdoor Attacks Against Deep Learning Systems in the Physical World","created":"2020-06-25","cited_by_count":134},{"id":"2510.09023","title":"The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections","created":"2025-10-10","cited_by_count":129},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126},{"id":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","created":"2025-11-20","cited_by_count":75},{"id":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71},{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68},{"id":"2508.12752","title":"Deep Research: A Survey of Autonomous Research Agents","created":"2025-08-18","cited_by_count":66},{"id":"2501.09674","title":"Authenticated Delegation and Authorized AI Agents","created":"2025-01-16","cited_by_count":65},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59},{"id":"2312.10766","title":"JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks","created":"2023-12-17","cited_by_count":50},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49},{"id":"2510.25445","title":"Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions","created":"2025-10-29","cited_by_count":48},{"id":"2409.16427","title":"HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions","created":"2024-09-24","cited_by_count":44},{"id":"2504.10374","title":"Ctrl-Z: Controlling AI Agents via Resampling","created":"2025-04-14","cited_by_count":44},{"id":"2507.03616","title":"EvoAgentX: An Automated Framework for Evolving Agentic Workflows","created":"2025-07-04","cited_by_count":44},{"id":"2505.14534","title":"Lessons from Defending Gemini Against Indirect Prompt Injections","created":"2025-05-20","cited_by_count":43},{"id":"2502.14296","title":"On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective","created":"2025-02-20","cited_by_count":41},{"id":"2510.19207","title":"Defending Against Prompt Injection with DataFilter","created":"2025-10-22","cited_by_count":35},{"id":"2502.13175","title":"Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks","created":"2025-02-18","cited_by_count":34},{"id":"2404.04442","title":"Exploring Autonomous Agents through the Lens of Large Language Models: A Review","created":"2024-04-05","cited_by_count":31},{"id":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29},{"id":"2409.01980","title":"Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey","created":"2024-09-03","cited_by_count":27},{"id":"2502.19145","title":"Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems","created":"2025-02-26","cited_by_count":27},{"id":"2402.00371","title":"What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection","created":"2024-02-01","cited_by_count":25},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24},{"id":"2404.12736","title":"Large Language Model Supply Chain: A Research Agenda","created":"2024-04-19","cited_by_count":23},{"id":"2406.07973","title":"Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey","created":"2024-06-12","cited_by_count":23},{"id":"2511.20920","title":"Securing the Model Context Protocol (MCP): Risks, Controls, and Governance","created":"2025-11-25","cited_by_count":23},{"id":"2407.21424","title":"Cost-Effective Hallucination Detection for LLMs","created":"2024-07-31","cited_by_count":18},{"id":"2512.04535","title":"GTM: Simulating the World of Tools for AI Agents","created":"2025-12-04","cited_by_count":14},{"id":"2303.12132","title":"Fundamentals of Generative Large Language Models and Perspectives in Cyber-Defense","created":"2023-03-21","cited_by_count":13},{"id":"2410.21083","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","created":"2024-10-28","cited_by_count":12},{"id":"1904.06292","title":"Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks","created":"2019-04-12","cited_by_count":11},{"id":"2507.13038","title":"MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems","created":"2025-07-17","cited_by_count":10},{"id":"2411.01604","title":"Large Language Model Supply Chain: Open Problems From the Security Perspective","created":"2024-11-03","cited_by_count":9},{"id":"2501.18002","title":"Agentic Workflows for Conversational Human-AI Interaction Design","created":"2025-01-29","cited_by_count":8},{"id":"2508.20890","title":"PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance","created":"2025-08-28","cited_by_count":8},{"id":"2310.06775","title":"Conceptual Framework for Autonomous Cognitive Entities","created":"2023-10-03","cited_by_count":6},{"id":"2410.19230","title":"Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors","created":"2024-10-25","cited_by_count":6},{"id":"2502.09955","title":"Diverse Inference and Verification for Advanced Reasoning","created":"2025-02-14","cited_by_count":6},{"id":"2105.06512","title":"Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs","created":"2021-05-13","cited_by_count":5},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5},{"id":"2412.08969","title":"Deep Learning Model Security: Threats and Defenses","created":"2024-12-12","cited_by_count":4},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4},{"id":"2508.11824","title":"Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering","created":"2025-08-15","cited_by_count":4},{"id":"2509.05883","title":"Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs","created":"2025-09-07","cited_by_count":4},{"id":"2407.03391","title":"Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning","created":"2024-07-03","cited_by_count":3},{"id":"2410.15396","title":"The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks","created":"2024-10-20","cited_by_count":3},{"id":"2407.05710","title":"Saltzer & Schroeder for 2030: Security engineering principles in a world of AI","created":"2024-07-08","cited_by_count":2},{"id":"2409.17283","title":"Investigating Privacy Attacks in the Gray-Box Setting to Enhance Collaborative Learning Schemes","created":"2024-09-25","cited_by_count":1},{"id":"2508.06153","title":"SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs","created":"2025-08-08","cited_by_count":1}],"next_cursor":null}