{"total":60,"rows":[{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2410.08115","title":"Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System","created":"2024-10-10","cited_by_count":43,"area":"agents"},{"id":"2405.20267","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","created":"2024-05-30","cited_by_count":42,"area":"agents"},{"id":"2502.07350","title":"KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems","created":"2025-02-11","cited_by_count":37,"area":"agents"},{"id":"2502.14074","title":"Investigating Non-Transitivity in LLM-as-a-Judge","created":"2025-02-19","cited_by_count":34,"area":"agents"},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2410.14251","title":"Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation","created":"2024-10-18","cited_by_count":24,"area":"agents"},{"id":"2502.17924","title":"FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models","created":"2025-02-25","cited_by_count":19,"area":"agents"},{"id":"2601.10343","title":"OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding","created":"2026-01-15","cited_by_count":15,"area":"agents"},{"id":"2606.09863","title":"From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents","created":"2026-06-01","cited_by_count":15,"area":"agents"},{"id":"2412.04494","title":"MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification","created":"2024-11-28","cited_by_count":12,"area":"agents"},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10,"area":"agents"},{"id":"2507.02735","title":"Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks","created":"2025-07-03","cited_by_count":10,"area":"agents"},{"id":"2510.08240","title":"The Alignment Waltz: Jointly Training Agents to Collaborate for Safety","created":"2025-10-09","cited_by_count":10,"area":"agents"},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2502.03821","title":"PsyPlay: Personality-Infused Role-Playing Conversational Agents","created":"2025-02-06","cited_by_count":9,"area":"agents"},{"id":"2604.10547","title":"Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?","created":"2026-04-12","cited_by_count":9,"area":"agents"},{"id":"2505.12531","title":"ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents","created":"2025-05-18","cited_by_count":8,"area":"agents"},{"id":"2606.20659","title":"Skill Coverage: A Test Adequacy Metric for Agent Skills","created":"2026-06-09","cited_by_count":8,"area":"agents"},{"id":"2607.02577","title":"Benchmarking the Benchmarks: A Validity Audit of Tool-Calling Evaluation","created":"2026-06-30","cited_by_count":8,"area":"agents"},{"id":"2601.04620","title":"AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering","created":"2026-01-08","cited_by_count":7,"area":"agents"},{"id":"2601.14230","title":"MASCOT: Multi-Agent Socio-Collaborative Companion Systems","created":"2026-01-20","cited_by_count":7,"area":"agents"},{"id":"2601.17887","title":"When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents","created":"2026-01-25","cited_by_count":7,"area":"agents"},{"id":"2602.03045","title":"Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation","created":"2026-02-03","cited_by_count":7,"area":"agents"},{"id":"2411.02457","title":"A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles","created":"2024-11-04","cited_by_count":6,"area":"agents"},{"id":"2601.10504","title":"DR-Arena: an Automated Evaluation Framework for Deep Research Agents","created":"2026-01-15","cited_by_count":6,"area":"agents"},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2510.09021","title":"RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows","created":"2025-10-10","cited_by_count":4,"area":"agents"},{"id":"2601.05899","title":"TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents","created":"2026-01-09","cited_by_count":4,"area":"agents"},{"id":"2604.10741","title":"Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation","created":"2026-04-12","cited_by_count":4,"area":"agents"},{"id":"2510.05059","title":"Staircase Streaming for Low-Latency Multi-Agent Inference","created":"2025-10-06","cited_by_count":3,"area":"agents"},{"id":"2601.16596","title":"Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesis","created":"2026-01-23","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":"2606.21169","title":"Trip+: Benchmarking Agents in Personalized Interactive Travel Planning","created":"2026-06-19","cited_by_count":3,"area":"agents"},{"id":"2511.03023","title":"PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2511.03051","title":"No-Human in the Loop: Agentic Evaluation at Scale for Recommendation","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2511.08835","title":"Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents","created":"2025-11-11","cited_by_count":2,"area":"agents"},{"id":"2602.11304","title":"CryptoAnalystBench: Failures in Multi-Tool Long-Form LLM Analysis","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2605.17554","title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2606.10296","title":"The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.29894","title":"SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics","created":"2026-06-29","cited_by_count":1,"area":"agents"},{"id":"2608.25937","title":"Candidate supply and answer selection shape the value of LLM judging in multi-agent systems","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.07785","title":"What Does an LLM-Agent Leaderboard Rank Actually Compare?","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2508.06963","title":"MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair","created":"2025-08-09","cited_by_count":0,"area":"agents"},{"id":"2511.10810","title":"HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments","created":"2025-11-13","cited_by_count":0,"area":"agents"},{"id":"2601.11854","title":"ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems","created":"2026-01-17","cited_by_count":0,"area":"agents"},{"id":"2602.15859","title":"From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants","created":"2026-01-26","cited_by_count":0,"area":"agents"},{"id":"2605.24699","title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.00931","title":"CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2607.12085","title":"Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.18529","title":"EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.20527","title":"Evaluating and Guarding Citation Faithfulness in Agentic Scientific Synthesis","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2608.08995","title":"Muscle Memory for Agents: Compile not Merely Retrieve","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.10224","title":"Self-evolving Agentic Customer Support System at LinkedIn","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.15877","title":"Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation","created":"2026-08-16","cited_by_count":0,"area":"agents"},{"id":"2609.00434","title":"SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.00621","title":"Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.06059","title":"DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.30471","title":"CARGO: Context-Aware Retrieval-Gated Evaluation of Agentic AI in Production","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.39958","title":"Better Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}