{"total":39,"rows":[{"id":"2505.00212","title":"Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems","created":"2025-04-30","cited_by_count":185,"area":"agents"},{"id":"2505.16997","title":"X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs","created":"2025-05-22","cited_by_count":38,"area":"agents"},{"id":"2508.02994","title":"When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs","created":"2025-08-05","cited_by_count":17,"area":"agents"},{"id":"2504.17087","title":"Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments","created":"2025-04-23","cited_by_count":16,"area":"agents"},{"id":"2505.18882","title":"Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach","created":"2025-05-24","cited_by_count":16,"area":"agents"},{"id":"2604.18240","title":"AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation","created":"2026-04-20","cited_by_count":12,"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":"2605.19196","title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","created":"2026-05-18","cited_by_count":10,"area":"agents"},{"id":"2508.02921","title":"PentestJudge: Judging Agent Behavior Against Operational Requirements","created":"2025-08-04","cited_by_count":7,"area":"agents"},{"id":"2606.29920","title":"Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?","created":"2026-06-29","cited_by_count":7,"area":"agents"},{"id":"2606.24595","title":"MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery","created":"2026-06-23","cited_by_count":6,"area":"agents"},{"id":"2502.12927","title":"SEFL: A Framework for Generating Synthetic Educational Assignment Feedback with LLM Agents","created":"2025-02-18","cited_by_count":3,"area":"agents"},{"id":"2602.13165","title":"Asynchronous Verified Semantic Caching for Tiered LLM Architectures","created":"2026-02-13","cited_by_count":3,"area":"agents"},{"id":"2603.09643","title":"MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings","created":"2026-03-10","cited_by_count":3,"area":"agents"},{"id":"2606.03980","title":"Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill","created":"2026-06-02","cited_by_count":3,"area":"agents"},{"id":"2609.12191","title":"GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents","created":"2026-09-10","cited_by_count":3,"area":"agents"},{"id":"2507.02182","title":"Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language Models","created":"2025-07-02","cited_by_count":2,"area":"agents"},{"id":"2604.26020","title":"Training Computer Use Agents to Assess the Usability of Graphical User Interfaces","created":"2026-04-28","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":"2510.19995","title":"Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication","created":"2025-10-22","cited_by_count":1,"area":"agents"},{"id":"2607.22465","title":"TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2608.05573","title":"SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2510.19423","title":"ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem","created":"2025-10-22","cited_by_count":0,"area":"agents"},{"id":"2604.08970","title":"Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models","created":"2026-04-10","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":"2604.17456","title":"TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2604.26235","title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","created":"2026-04-29","cited_by_count":0,"area":"agents"},{"id":"2606.17789","title":"Mind Companion: An Embodied Conversational Agent for Process-Based Psychotherapy","created":"2026-06-16","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":"2606.30887","title":"Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2607.14642","title":"MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers","created":"2026-07-16","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":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.29578","title":"PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.33955","title":"Designing Reliable LLM-as-a-Judge Measurement Systems for Multi-Turn Business Agents","created":"2026-09-27","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":"2610.04686","title":"When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning","created":"2026-10-03","cited_by_count":0,"area":"agents"}],"next_cursor":null}