{"total":20,"rows":[{"id":"2504.08725","title":"DocAgent: A Multi-Agent System for Automated Code Documentation Generation","created":"2025-04-11","cited_by_count":18,"area":"agents"},{"id":"2506.22598","title":"RExBench: Can coding agents autonomously implement AI research extensions?","created":"2025-06-27","cited_by_count":18,"area":"agents"},{"id":"2410.15287","title":"Training Language Models to Critique With Multi-agent Feedback","created":"2024-10-20","cited_by_count":16,"area":"agents"},{"id":"2512.17776","title":"DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation","created":"2025-12-19","cited_by_count":12,"area":"agents"},{"id":"2605.07161","title":"SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2607.01236","title":"Safeguarding LLM Agents from Misalignment through Provenance Analysis","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2601.13217","title":"Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision","created":"2026-01-19","cited_by_count":4,"area":"agents"},{"id":"2608.11683","title":"FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2511.17689","title":"ARISE: Agentic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper Generation","created":"2025-11-21","cited_by_count":3,"area":"agents"},{"id":"2505.01592","title":"AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents","created":"2025-05-02","cited_by_count":2,"area":"agents"},{"id":"2605.29256","title":"DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2608.01708","title":"PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2608.08160","title":"Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives","created":"2026-08-08","cited_by_count":2,"area":"agents"},{"id":"2603.20884","title":"MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessment","created":"2026-03-21","cited_by_count":1,"area":"agents"},{"id":"2607.18886","title":"TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development","created":"2026-07-21","cited_by_count":1,"area":"agents"},{"id":"2608.27487","title":"Grounded Checklist Partial Credit for Agent Skill Trajectories","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.22942","title":"An Evolutionary Agentic Approach for Open-ended Image Quality Perception","created":"2026-09-19","cited_by_count":1,"area":"agents"},{"id":"2602.11198","title":"Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability","created":"2026-02-03","cited_by_count":0,"area":"agents"},{"id":"2609.14178","title":"A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement","created":"2026-09-12","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"}],"next_cursor":null}