{"total":51,"rows":[{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2503.01763","title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","created":"2025-03-03","cited_by_count":47,"area":"agents"},{"id":"2602.17753","title":"The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems","created":"2026-02-19","cited_by_count":30,"area":"agents"},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15,"area":"agents"},{"id":"2604.05485","title":"Auditable Agents","created":"2026-04-07","cited_by_count":15,"area":"agents"},{"id":"2410.21909","title":"SceneGenAgent: Precise Industrial Scene Generation with Coding Agent","created":"2024-10-29","cited_by_count":13,"area":"agents"},{"id":"2603.11337","title":"RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents","created":"2026-03-11","cited_by_count":10,"area":"agents"},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2605.18859","title":"TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2605.21404","title":"What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema","created":"2026-05-20","cited_by_count":6,"area":"agents"},{"id":"2406.15341","title":"GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis","created":"2024-06-21","cited_by_count":5,"area":"agents"},{"id":"2605.07728","title":"SARC: A Governance-by-Architecture Framework for Agentic AI Systems","created":"2026-05-08","cited_by_count":5,"area":"agents"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2502.00858","title":"Inferring the Unspoken: Aligning Embodied Agents with Implicit Preferences","created":"2025-02-02","cited_by_count":4,"area":"agents"},{"id":"2604.01532","title":"PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools","created":"2026-04-02","cited_by_count":4,"area":"agents"},{"id":"2605.04785","title":"AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use","created":"2026-05-06","cited_by_count":4,"area":"agents"},{"id":"2606.21877","title":"AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems","created":"2026-06-20","cited_by_count":4,"area":"agents"},{"id":"2607.10490","title":"NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations","created":"2026-07-11","cited_by_count":4,"area":"agents"},{"id":"2608.11727","title":"Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2609.09218","title":"The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean","created":"2026-09-06","cited_by_count":3,"area":"agents"},{"id":"2505.17511","title":"Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identification","created":"2025-05-23","cited_by_count":2,"area":"agents"},{"id":"2605.03310","title":"Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems","created":"2026-05-05","cited_by_count":2,"area":"agents"},{"id":"2605.28158","title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2609.06972","title":"AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories","created":"2026-09-07","cited_by_count":2,"area":"agents"},{"id":"2604.10261","title":"The Amazing Agent Race: Strong Tool Users, Weak Navigators","created":"2026-04-11","cited_by_count":1,"area":"agents"},{"id":"2606.08857","title":"PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf","created":"2026-06-07","cited_by_count":1,"area":"agents"},{"id":"2607.26064","title":"The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Science","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2609.22200","title":"PII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM Conversations","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.40111","title":"Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2510.21370","title":"HIKMA: Human-Inspired Knowledge by Machine Agents through a Multi-Agent Framework for Semi-Autonomous Scientific Conferences","created":"2025-10-24","cited_by_count":0,"area":"agents"},{"id":"2601.15114","title":"From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media","created":"2026-01-21","cited_by_count":0,"area":"agents"},{"id":"2601.22288","title":"PersonaCite: VoC-Grounded Interviewable Agentic Synthetic AI Personas for Verifiable User and Design Research","created":"2026-01-29","cited_by_count":0,"area":"agents"},{"id":"2603.06599","title":"Building the ethical AI framework of the future: from philosophy to practice","created":"2026-02-16","cited_by_count":0,"area":"agents"},{"id":"2603.21698","title":"A Blueprint for Self-Evolving Coding Agents in Vehicle Aerodynamic Drag Prediction","created":"2026-03-23","cited_by_count":0,"area":"agents"},{"id":"2604.06013","title":"Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis","created":"2026-04-07","cited_by_count":0,"area":"agents"},{"id":"2605.04637","title":"SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2606.15485","title":"The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Products","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2606.19356","title":"Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2606.21959","title":"OpenBioRQ: Unsolved Biomedical Research Questions for Agents","created":"2026-06-20","cited_by_count":0,"area":"agents"},{"id":"2606.23403","title":"Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems","created":"2026-06-22","cited_by_count":0,"area":"agents"},{"id":"2607.00436","title":"PHREEQC-MCQ-200: A Diagnostic Benchmark for Tool-Augmented Scientific Simulator Agents","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.07676","title":"SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2608.08601","title":"Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents","created":"2026-08-09","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":"2608.15591","title":"Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback","created":"2026-08-16","cited_by_count":0,"area":"agents"},{"id":"2608.26086","title":"TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2608.26204","title":"ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.01271","title":"What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels Reveal","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.21325","title":"LEGIT: Credentialing Protocol for Trustworthy AI Agent Marketplaces","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.27571","title":"FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2610.04544","title":"Label Agreement Does Not Measure Authorization","created":"2026-10-03","cited_by_count":0,"area":"agents"}],"next_cursor":null}