{"total":30,"rows":[{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"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":"2601.08536","title":"DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports","created":"2026-01-13","cited_by_count":34,"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":"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":"2606.09863","title":"From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents","created":"2026-06-01","cited_by_count":15,"area":"agents"},{"id":"2412.21102","title":"Exploring and Controlling Diversity in LLM-Agent Conversation","created":"2024-12-30","cited_by_count":12,"area":"agents"},{"id":"2507.01413","title":"Evaluating LLM Agent Collusion in Double Auctions","created":"2025-07-02","cited_by_count":11,"area":"agents"},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10,"area":"agents"},{"id":"2605.19769","title":"OpenComputer: Verifiable Software Worlds for Computer-Use Agents","created":"2026-05-19","cited_by_count":10,"area":"agents"},{"id":"2504.02867","title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications","created":"2025-04-01","cited_by_count":7,"area":"agents"},{"id":"2601.08118","title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness","created":"2026-01-13","cited_by_count":7,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2506.11825","title":"Revealing Political Bias in LLMs through Structured Multi-Agent Debate","created":"2025-06-13","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"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":"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":"2605.28158","title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"area":"agents"},{"id":"2410.14041","title":"From Barriers to Tactics: A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching","created":"2024-10-17","cited_by_count":1,"area":"agents"},{"id":"2609.06027","title":"Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning","created":"2026-09-05","cited_by_count":1,"area":"agents"},{"id":"2609.06128","title":"Substrate-Portable Execution for Production LLM Workflows","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.06783","title":"AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.22209","title":"Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.30471","title":"CARGO: Context-Aware Retrieval-Gated Evaluation of Agentic AI in Production","created":"2026-09-24","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":"2609.39958","title":"Better Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.13273","title":"Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.17206","title":"AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.19433","title":"EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}