{"total":17,"rows":[{"id":"2310.10158","title":"Character-LLM: A Trainable Agent for Role-Playing","created":"2023-10-16","cited_by_count":339,"area":"agents"},{"id":"2406.03075","title":"Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework","created":"2024-06-05","cited_by_count":19,"area":"agents"},{"id":"2502.08514","title":"Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation","created":"2025-02-12","cited_by_count":10,"area":"agents"},{"id":"2605.08580","title":"Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents","created":"2026-05-09","cited_by_count":6,"area":"agents"},{"id":"2606.18037","title":"ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2505.09938","title":"Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studies","created":"2025-05-15","cited_by_count":2,"area":"agents"},{"id":"2608.24569","title":"When \"Must\" Becomes \"Maybe\": Constraint Weakening in LLM Agent Workflows","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2509.26433","title":"ACT: Agentic Classification Tree","created":"2025-09-30","cited_by_count":1,"area":"agents"},{"id":"2603.14997","title":"OrgForge: A Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora","created":"2026-03-16","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":"2608.22752","title":"The Compaction Cliff in Long-Running AI Agent Memory","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2602.20040","title":"AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization","created":"2026-02-23","cited_by_count":0,"area":"agents"},{"id":"2605.08462","title":"Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2607.10390","title":"A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"id":"2607.24770","title":"ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2609.17842","title":"Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics Agents","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2610.19659","title":"Measuring and Reducing Unusable Replies of LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}