{"total":30,"rows":[{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006,"area":"agents"},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"id":"2409.13740","title":"Language agents achieve superhuman synthesis of scientific knowledge","created":"2024-09-10","cited_by_count":137,"area":"agents"},{"id":"2502.19130","title":"Voting or Consensus? Decision-Making in Multi-Agent Debate","created":"2025-02-26","cited_by_count":59,"area":"agents"},{"id":"2403.08140","title":"BAGEL: Bootstrapping Agents by Guiding Exploration with Language","created":"2024-03-12","cited_by_count":34,"area":"agents"},{"id":"2505.22655","title":"Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents","created":"2025-05-28","cited_by_count":32,"area":"agents"},{"id":"2404.01663","title":"CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models","created":"2024-04-02","cited_by_count":26,"area":"agents"},{"id":"2410.22932","title":"Multi-Agent Large Language Models for Conversational Task-Solving","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2602.10715","title":"Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents","created":"2026-02-11","cited_by_count":19,"area":"agents"},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2412.01033","title":"SAUP: Situation Awareness Uncertainty Propagation on LLM Agent","created":"2024-12-02","cited_by_count":14,"area":"agents"},{"id":"2410.14735","title":"Agent Skill Acquisition for Large Language Models via CycleQD","created":"2024-10-16","cited_by_count":12,"area":"agents"},{"id":"2603.26499","title":"AIRA_2: Overcoming Bottlenecks in AI Research Agents","created":"2026-03-27","cited_by_count":12,"area":"agents"},{"id":"2410.15701","title":"When LLMs Learn to be Students: The SOEI Framework for Modeling and Evaluating Virtual Student Agents in Educational Interaction","created":"2024-10-21","cited_by_count":4,"area":"agents"},{"id":"2505.15063","title":"UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking","created":"2025-05-21","cited_by_count":4,"area":"agents"},{"id":"2511.00739","title":"Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective","created":"2025-11-01","cited_by_count":4,"area":"agents"},{"id":"2605.15030","title":"WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2604.11419","title":"Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval","created":"2026-04-13","cited_by_count":3,"area":"agents"},{"id":"2608.00432","title":"Deep Research Pretraining via Predictive Navigation","created":"2026-08-01","cited_by_count":3,"area":"agents"},{"id":"2604.22861","title":"IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review","created":"2026-04-23","cited_by_count":2,"area":"agents"},{"id":"2605.05379","title":"Partial Evidence Bench: Benchmarking Authorization-Limited Evidence in Agentic Systems","created":"2026-05-06","cited_by_count":2,"area":"agents"},{"id":"2307.07255","title":"Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems","created":"2023-07-14","cited_by_count":1,"area":"agents"},{"id":"2504.05607","title":"FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction","created":"2025-04-08","cited_by_count":1,"area":"agents"},{"id":"2608.05519","title":"EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.07899","title":"TelemetrySuffBench: Is Agent Telemetry Sufficient for Failure-Origin Diagnosis?","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2610.05107","title":"SearchJev: A Fast and Calibrated System-1 Model for Search Agents","created":"2026-10-04","cited_by_count":1,"area":"agents"},{"id":"2507.03726","title":"Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Models","created":"2025-07-04","cited_by_count":0,"area":"agents"},{"id":"2606.03812","title":"Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2607.07397","title":"Agentic Data Environments","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2610.05223","title":"Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}