{"total":32,"rows":[{"id":"2410.12189","title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","created":"2024-10-16","cited_by_count":52,"area":"agents"},{"id":"2507.21028","title":"Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation","created":"2025-07-28","cited_by_count":30,"area":"agents"},{"id":"2505.02847","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","created":"2025-05-01","cited_by_count":21,"area":"agents"},{"id":"2601.05111","title":"Agent-as-a-Judge","created":"2026-01-08","cited_by_count":17,"area":"agents"},{"id":"2603.21362","title":"AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning","created":"2026-03-22","cited_by_count":13,"area":"agents"},{"id":"2505.19477","title":"Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge","created":"2025-05-26","cited_by_count":11,"area":"agents"},{"id":"2607.00692","title":"Self-GC: Self-Governing Context for Long-Horizon LLM Agents","created":"2026-07-01","cited_by_count":11,"area":"agents"},{"id":"2510.24358","title":"Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation","created":"2025-10-28","cited_by_count":9,"area":"agents"},{"id":"2601.15232","title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","created":"2026-01-21","cited_by_count":6,"area":"agents"},{"id":"2510.04787","title":"Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2510.16194","title":"Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaboration","created":"2025-10-17","cited_by_count":3,"area":"agents"},{"id":"2511.06396","title":"Efficient LLM Safety Evaluation through Multi-Agent Debate","created":"2025-11-09","cited_by_count":2,"area":"agents"},{"id":"2605.17439","title":"DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2608.26623","title":"AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling","created":"2026-08-27","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":"2604.14683","title":"DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation","created":"2026-04-16","cited_by_count":1,"area":"agents"},{"id":"2608.11434","title":"Benchmarking LLM Judges for Mobile Agent Evaluation","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"id":"2608.13564","title":"Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2609.29718","title":"PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2510.03771","title":"OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation","created":"2025-10-04","cited_by_count":0,"area":"agents"},{"id":"2511.17621","title":"From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems","created":"2025-11-18","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":"2604.09564","title":"ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness","created":"2026-02-14","cited_by_count":0,"area":"agents"},{"id":"2605.19180","title":"Supporting System Testing with a Multi-Agent LLM-based Framework for Knowledge Graph Extraction: A Case Study with Ethernet Switch Systems","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2606.23032","title":"IPO Finance Agent: Benchmark of LLM Financial Analysts Beyond Finance Agent v2, with Automated Rubric Generation, on the SpaceX (SPCX) IPO","created":"2026-06-22","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":"2609.19705","title":"SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.22258","title":"RS-Claw-Evolution: Environment-Feedback-Driven Evolution for Lightweight Remote Sensing Agents in Long-Horizon Tasks","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.34320","title":"Certified Selective Automation of LLM Agent Evaluation","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36086","title":"PADMÉ: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.04087","title":"DUET: Co-Evolving Solver and Grader Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04672","title":"MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability","created":"2026-10-03","cited_by_count":0,"area":"agents"}],"next_cursor":null}