{"total":74,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2410.02644","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","created":"2024-10-03","cited_by_count":369,"area":"agents"},{"id":"2410.14923","title":"Imprompter: Tricking LLM Agents into Improper Tool Use","created":"2024-10-19","cited_by_count":68,"area":"agents"},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"id":"2504.06196","title":"TxGemma: Efficient and Agentic LLMs for Therapeutics","created":"2025-04-08","cited_by_count":41,"area":"agents"},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"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":"2504.00218","title":"$\\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks","created":"2025-03-31","cited_by_count":34,"area":"agents"},{"id":"2501.13299","title":"Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents","created":"2025-01-23","cited_by_count":30,"area":"agents"},{"id":"2411.00053","title":"ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2502.14529","title":"CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models","created":"2025-02-20","cited_by_count":20,"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":"2412.01605","title":"Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence","created":"2024-12-02","cited_by_count":17,"area":"agents"},{"id":"2504.21716","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","created":"2025-04-30","cited_by_count":17,"area":"agents"},{"id":"2505.00416","title":"ScaleTrack: Scaling and back-tracking Automated GUI Agents","created":"2025-05-01","cited_by_count":16,"area":"agents"},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2604.23626","title":"GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs","created":"2026-04-26","cited_by_count":12,"area":"agents"},{"id":"2502.11882","title":"Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration","created":"2025-02-17","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":"2410.03335","title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","created":"2024-10-04","cited_by_count":9,"area":"agents"},{"id":"2505.02133","title":"Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency","created":"2025-05-04","cited_by_count":9,"area":"agents"},{"id":"2504.03553","title":"Agentic Knowledgeable Self-awareness","created":"2025-04-04","cited_by_count":8,"area":"agents"},{"id":"2510.24303","title":"Retrieval- and Argumentation-Enhanced Multi-Agent LLMs for Judgmental Forecasting (Extended Version with Supplementary Material)","created":"2025-10-28","cited_by_count":8,"area":"agents"},{"id":"2505.10872","title":"REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?","created":"2025-05-16","cited_by_count":7,"area":"agents"},{"id":"2505.24442","title":"RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation","created":"2025-05-30","cited_by_count":7,"area":"agents"},{"id":"2501.05255","title":"CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing","created":"2025-01-09","cited_by_count":6,"area":"agents"},{"id":"2505.21963","title":"LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents","created":"2025-05-28","cited_by_count":6,"area":"agents"},{"id":"2507.02197","title":"Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust","created":"2025-07-02","cited_by_count":6,"area":"agents"},{"id":"2511.07322","title":"FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation","created":"2025-11-10","cited_by_count":6,"area":"agents"},{"id":"2411.04671","title":"CUIfy the XR: An Open-Source Package to Embed LLM-powered Conversational Agents in XR","created":"2024-11-07","cited_by_count":5,"area":"agents"},{"id":"2412.00402","title":"DroidCall: A Dataset for LLM-powered Android Intent Invocation","created":"2024-11-30","cited_by_count":5,"area":"agents"},{"id":"2507.23554","title":"DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer","created":"2025-07-31","cited_by_count":5,"area":"agents"},{"id":"2510.15455","title":"CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs","created":"2025-10-17","cited_by_count":5,"area":"agents"},{"id":"2511.04393","title":"Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach","created":"2025-11-06","cited_by_count":5,"area":"agents"},{"id":"2605.01555","title":"Automated Interpretability and Feature Discovery in Language Models with Agents","created":"2026-05-02","cited_by_count":4,"area":"agents"},{"id":"2411.04496","title":"Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model","created":"2024-11-07","cited_by_count":3,"area":"agents"},{"id":"2502.15690","title":"Level-Navi Agent: A Framework and benchmark for Chinese Web Search Agents","created":"2024-12-20","cited_by_count":3,"area":"agents"},{"id":"2507.08440","title":"Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences","created":"2025-07-11","cited_by_count":3,"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":"2511.20940","title":"Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs","created":"2025-11-26","cited_by_count":3,"area":"agents"},{"id":"2601.03671","title":"NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models","created":"2026-01-07","cited_by_count":3,"area":"agents"},{"id":"2603.11132","title":"WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"id":"2603.25268","title":"CRAFT: Grounded Multi-Agent Coordination Under Partial Information","created":"2026-03-26","cited_by_count":3,"area":"agents"},{"id":"2605.12991","title":"Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy","created":"2026-05-13","cited_by_count":3,"area":"agents"},{"id":"2607.29626","title":"AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2502.11649","title":"Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation","created":"2025-02-17","cited_by_count":2,"area":"agents"},{"id":"2502.18308","title":"RefuteBench 2.0 -- Agentic Benchmark for Dynamic Evaluation of LLM Responses to Refutation Instruction","created":"2025-02-25","cited_by_count":2,"area":"agents"},{"id":"2510.08255","title":"Opponent Shaping in LLM Agents","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2604.16543","title":"Conjunctive Prompt Attacks in Multi-Agent LLM Systems","created":"2026-04-17","cited_by_count":2,"area":"agents"},{"id":"2607.02186","title":"UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development","created":"2026-07-02","cited_by_count":2,"area":"agents"},{"id":"2607.05318","title":"PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems","created":"2026-07-06","cited_by_count":2,"area":"agents"},{"id":"2511.07112","title":"More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists","created":"2025-11-10","cited_by_count":1,"area":"agents"},{"id":"2601.20375","title":"LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2602.00028","title":"ELLMPEG: An Edge-based Agentic LLM Video Processing Tool","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2604.16941","title":"MEMRES: A Memory-Augmented Resolver with Confidence Cascade for Agentic Python Dependency Resolution","created":"2026-04-18","cited_by_count":1,"area":"agents"},{"id":"2606.31522","title":"FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2608.05199","title":"Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.12547","title":"Do LLMs Beat Nash? Testing Decentralized Coordination in Self-Play Multi-Agent Games","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2609.01272","title":"Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2511.07392","title":"Voice-Interactive Surgical Agent for Multimodal Patient Data Control","created":"2025-11-10","cited_by_count":0,"area":"agents"},{"id":"2601.14091","title":"Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems","created":"2026-01-20","cited_by_count":0,"area":"agents"},{"id":"2603.16901","title":"From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning","created":"2026-03-04","cited_by_count":0,"area":"agents"},{"id":"2604.17191","title":"Do LLM-derived graph priors improve multi-agent coordination?","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2605.29625","title":"Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language Models","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2606.29030","title":"Memory as an Attack Surface in LLM Agents: A Study on Multiple-Choice Question Answering","created":"2026-06-27","cited_by_count":0,"area":"agents"},{"id":"2606.31307","title":"When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2608.22063","title":"From SQL Generation to Tool Selection: A Domain-Oriented Pattern for MCP Servers","created":"2026-08-22","cited_by_count":0,"area":"agents"},{"id":"2609.13470","title":"OrchSLM: Probing the Dynamics of Small Language Model Orchestration","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.17552","title":"Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2609.18357","title":"Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.25570","title":"Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.38866","title":"When Context Changes: Understanding Update Failures in LLMs","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00430","title":"Memetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.15095","title":"Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}