{"total":89,"rows":[{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627,"area":null},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468,"area":null},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"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,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2501.17070","title":"Contextual Agent Security: A Policy for Every Purpose","created":"2025-01-28","cited_by_count":59,"area":null},{"id":"2402.04247","title":"Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2410.07137","title":"Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates","created":"2024-10-09","cited_by_count":45,"area":null},{"id":"2403.11085","title":"m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks","created":"2024-03-17","cited_by_count":38,"area":null},{"id":"2408.02373","title":"Operationalizing Contextual Integrity in Privacy-Conscious Assistants","created":"2024-08-05","cited_by_count":37,"area":null},{"id":"2401.16467","title":"ReGAL: Refactoring Programs to Discover Generalizable Abstractions","created":"2024-01-29","cited_by_count":36,"area":null},{"id":"2406.05720","title":"VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft","created":"2024-06-09","cited_by_count":35,"area":null},{"id":"2505.14590","title":"MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol","created":"2025-05-20","cited_by_count":34,"area":null},{"id":"2312.07413","title":"AI capabilities can be significantly improved without expensive retraining","created":"2023-12-12","cited_by_count":28,"area":null},{"id":"2505.19933","title":"Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making","created":"2025-05-26","cited_by_count":20,"area":null},{"id":"2505.19212","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2504.04716","title":"On the Robustness of GUI Grounding Models Against Image Attacks","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2508.03284","title":"ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools","created":"2025-08-05","cited_by_count":13,"area":null},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2607.28802","title":"Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures","created":"2026-07-30","cited_by_count":10,"area":null},{"id":"2406.16714","title":"AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2507.17186","title":"FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domain","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2406.13161","title":"APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2512.14754","title":"Revisiting the Reliability of Language Models in Instruction-Following","created":"2025-12-15","cited_by_count":7,"area":null},{"id":"2606.14832","title":"PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2608.04289","title":"SafeCommit: Certifying When Memory-Grounded Agents May Safely Act","created":"2026-08-04","cited_by_count":6,"area":null},{"id":"2603.17170","title":"Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2606.22916","title":"Intent-Governed Tool Authorization for AI Agents","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2507.16124","title":"Benchmarking LLM Privacy Recognition for Social Robot Decision Making","created":"2025-07-22","cited_by_count":4,"area":null},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2605.11003","title":"The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2605.10516","title":"Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2607.21763","title":"Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2509.21143","title":"Automotive-ENV: Benchmarking Multimodal Agents in Vehicle Interface Systems","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2607.02345","title":"SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.25364","title":"Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2510.09674","title":"Leveraging LLMs to Streamline the Review of Public Funding Applications","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2604.20496","title":"Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.07247","title":"EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.07462","title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.13825","title":"History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.25815","title":"Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.05842","title":"Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2607.09744","title":"A Theory of Least Autonomy in AI","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.10455","title":"ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2608.18136","title":"FraudBench: Stress-Testing Policy-Grounded Banking Agents Against Adaptive Fraud","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2609.21284","title":"Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2609.30325","title":"ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?","created":"2026-09-23","cited_by_count":1,"area":null},{"id":"2609.35732","title":"Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2403.18205","title":"Exploring the Privacy Protection Capabilities of Chinese Large Language Models","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2506.00197","title":"When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2603.11001","title":"RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.09963","title":"Rebooting Microreboot: Architectural Support for Safe, Parallel Recovery in Microservice Systems","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2605.02661","title":"AcademiClaw: When Students Set Challenges for AI Agents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.11378","title":"An Empirical Study of Automating Agent Evaluation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.12856","title":"Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.03163","title":"OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.20487","title":"OctoNest: Adaptive Cross-Device Execution through Stateful Control","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31272","title":"The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.04613","title":"Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.05484","title":"SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.09489","title":"Ceci n'est pas une pipe: AI systems as semantic abstractions","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.17986","title":"Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.03866","title":"ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.25067","title":"SimVerity: When Does Simulated Agent Success Survive Physical Deployment?","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.00519","title":"The Safeguard Worked. Is the LLM System Safer?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02168","title":"FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.10724","title":"Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.11504","title":"DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.14400","title":"Policy Loopholes in Agent Evaluation: When Policy Ambiguity Masquerades as Agent Error","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.31186","title":"Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.35117","title":"Tool Mediation Alters Refusal Mechanisms in Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38460","title":"NAQD Env: A benchmark for selective withdrawal in language agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38469","title":"The Backdrop Exposes What the World Around an Agent Costs It","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38983","title":"Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00008","title":"Bounded-Fidelity Sim-as-Demo-Stage: Mocap Handoff for Governance Benchmarks","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2610.00015","title":"From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.04836","title":"RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.04975","title":"Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05532","title":"DelegationBench: Measuring When AI Agents Should Ask Before Acting","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.06914","title":"A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13623","title":"APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16280","title":"agent-risk: Risk Assessment for Changes to AI Agents","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18612","title":"Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20049","title":"CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}