{"total":36,"rows":[{"id":"2504.01382","title":"An Illusion of Progress? Assessing the Current State of Web Agents","created":"2025-04-02","cited_by_count":174,"area":"agents"},{"id":"2604.22840","title":"AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards","created":"2026-04-21","cited_by_count":11,"area":"agents"},{"id":"2509.19236","title":"AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration","created":"2025-09-23","cited_by_count":10,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2606.22737","title":"GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation","created":"2026-06-22","cited_by_count":6,"area":"agents"},{"id":"2507.11299","title":"Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian","created":"2025-07-15","cited_by_count":5,"area":"agents"},{"id":"2606.10315","title":"Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agents","created":"2026-06-09","cited_by_count":4,"area":"agents"},{"id":"2509.09685","title":"TalkPlayData 2: An Agentic Synthetic Data Pipeline for Multimodal Conversational Music Recommendation","created":"2025-08-18","cited_by_count":3,"area":"agents"},{"id":"2601.19793","title":"CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing","created":"2026-01-27","cited_by_count":3,"area":"agents"},{"id":"2603.04582","title":"Self-Attribution Bias: When AI Monitors Go Easy on Themselves","created":"2026-03-04","cited_by_count":3,"area":"agents"},{"id":"2608.00017","title":"Memory Reward Inflation in Self-Improving LLM Agents","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2509.26080","title":"Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research","created":"2025-09-30","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":"2601.18027","title":"Sentipolis: Emotion-Aware Agents for Social Simulations","created":"2026-01-25","cited_by_count":2,"area":"agents"},{"id":"2601.08156","title":"Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptions","created":"2026-01-13","cited_by_count":1,"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":"2605.06731","title":"When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.28369","title":"CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict","created":"2026-05-27","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":"2608.00794","title":"Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2603.21178","title":"LLM-based Automated Architecture View Generation: Where Are We Now?","created":"2026-03-22","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":"2606.20632","title":"Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2606.21627","title":"Counsel: A Meta-Evaluation Dataset for Agentic Tasks","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2607.01584","title":"EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.25485","title":"PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.08700","title":"PluginEval: A Diagnostic Benchmark for Fine-Grained Error Attribution in Function Calling","created":"2026-08-09","cited_by_count":0,"area":"agents"},{"id":"2608.20786","title":"Structure for Reading, Prose for Writing: Asymmetric Structural Conditioning in Multi-Agent Document Authoring","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.23740","title":"AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.30373","title":"Beyond Consensus: Downward Bias and Role Asymmetry in Multi-Agent LLM Judges for Subjective Evaluation","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.13422","title":"Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.14157","title":"When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"id":"2609.14758","title":"Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.18272","title":"Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.35928","title":"Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.16402","title":"EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}