{"list":"other","total":55,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2312.14197","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","created":"2023-12-21","cited_by_count":264},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232},{"id":"2311.07689","title":"MART: Improving LLM Safety with Multi-round Automatic Red-Teaming","created":"2023-11-13","cited_by_count":163},{"id":"2402.13457","title":"A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models","created":"2024-02-21","cited_by_count":106},{"id":"2405.17238","title":"IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities","created":"2024-05-27","cited_by_count":103},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79},{"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":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56},{"id":"2504.20984","title":"ACE: A Security Architecture for LLM-Integrated App Systems","created":"2025-04-29","cited_by_count":55},{"id":"2501.18160","title":"RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing","created":"2025-01-30","cited_by_count":49},{"id":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43},{"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":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30},{"id":"2503.09002","title":"KNighter: Transforming Static Analysis with LLM-Synthesized Checkers","created":"2025-03-12","cited_by_count":24},{"id":"2410.14827","title":"Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment","created":"2024-10-18","cited_by_count":21},{"id":"2305.12872","title":"Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game","created":"2023-05-22","cited_by_count":18},{"id":"2407.05194","title":"LLMCloudHunter: Harnessing LLMs for Automated Extraction of Detection Rules from Cloud-Based CTI","created":"2024-07-06","cited_by_count":18},{"id":"2503.04479","title":"ToolFuzz -- Automated Agent Tool Testing","created":"2025-03-06","cited_by_count":18},{"id":"2310.08535","title":"Formally Specifying the High-Level Behavior of LLM-Based Agents","created":"2023-10-12","cited_by_count":15},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14},{"id":"2508.18947","title":"LLMs in the SOC: An Empirical Study of Human-AI Collaboration in Security Operations Centres","created":"2025-08-26","cited_by_count":14},{"id":"2502.04227","title":"Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks","created":"2025-02-06","cited_by_count":12},{"id":"2410.17141","title":"Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements","created":"2024-10-22","cited_by_count":11},{"id":"2507.00829","title":"On the Surprising Efficacy of LLMs for Penetration-Testing","created":"2025-07-01","cited_by_count":10},{"id":"2404.04306","title":"AuditGPT: Auditing Smart Contracts with ChatGPT","created":"2024-04-05","cited_by_count":9},{"id":"2502.02009","title":"LLMSecConfig: An LLM-Based Approach for Fixing Software Container Misconfigurations","created":"2025-02-04","cited_by_count":9},{"id":"2506.12270","title":"Cloud Infrastructure Management in the Age of AI Agents","created":"2025-06-13","cited_by_count":9},{"id":"2507.04105","title":"Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing","created":"2025-07-05","cited_by_count":9},{"id":"2508.21302","title":"Locus: Agentic Predicate Synthesis for Directed Fuzzing","created":"2025-08-29","cited_by_count":9},{"id":"2504.17669","title":"Towards a HIPAA Compliant Agentic AI System in Healthcare","created":"2025-04-24","cited_by_count":8},{"id":"2506.06518","title":"A Systematic Review of Poisoning Attacks Against Large Language Models","created":"2025-06-06","cited_by_count":8},{"id":"2508.19870","title":"Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey","created":"2025-08-27","cited_by_count":8},{"id":"2508.10677","title":"Advancing Autonomous Incident Response: Leveraging LLMs and Cyber Threat Intelligence","created":"2025-08-14","cited_by_count":6},{"id":"2410.23678","title":"Goal Hijacking Attack on Large Language Models via Pseudo-Conversation Injection","created":"2024-10-31","cited_by_count":4},{"id":"2501.01664","title":"BARTPredict: Empowering IoT Security with LLM-Driven Cyber Threat Prediction","created":"2025-01-03","cited_by_count":4},{"id":"2509.02449","title":"KubeIntellect: A Modular LLM-Orchestrated Agent Framework for End-to-End Kubernetes Management","created":"2025-09-02","cited_by_count":4},{"id":"2502.13167","title":"SmartLLM: Smart Contract Auditing using Custom Generative AI","created":"2025-02-17","cited_by_count":3},{"id":"2506.07586","title":"MalGEN: A Testbed for Modeling and Evaluating Malware Behaviors","created":"2025-06-09","cited_by_count":3},{"id":"2507.13474","title":"Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers","created":"2025-07-17","cited_by_count":3},{"id":"2510.00452","title":"Cloud Investigation Automation Framework (CIAF): An AI-Driven Approach to Cloud Forensics","created":"2025-10-01","cited_by_count":3},{"id":"2510.02325","title":"Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP Agents","created":"2025-09-25","cited_by_count":1}],"next_cursor":null}