{"total":18,"rows":[{"id":"2401.04259","title":"MARG: Multi-Agent Review Generation for Scientific Papers","created":"2024-01-08","cited_by_count":104,"area":"agents"},{"id":"2505.19955","title":"MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research","created":"2025-05-26","cited_by_count":64,"area":"agents"},{"id":"2605.03042","title":"ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration","created":"2026-05-04","cited_by_count":16,"area":"agents"},{"id":"2506.19724","title":"From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking","created":"2025-06-24","cited_by_count":12,"area":"agents"},{"id":"2601.12910","title":"SciCoQA: Quality Assurance for Scientific Paper--Code Alignment","created":"2026-01-19","cited_by_count":10,"area":"agents"},{"id":"2606.24530","title":"NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?","created":"2026-06-23","cited_by_count":10,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2510.18003","title":"BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?","created":"2025-10-20","cited_by_count":8,"area":"agents"},{"id":"2606.13349","title":"From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent","created":"2026-06-11","cited_by_count":4,"area":"agents"},{"id":"2606.18237","title":"ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2606.08857","title":"PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf","created":"2026-06-07","cited_by_count":1,"area":"agents"},{"id":"2606.19749","title":"Benchmarking Agentic Review Systems","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2601.12988","title":"PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient","created":"2026-01-19","cited_by_count":0,"area":"agents"},{"id":"2604.04341","title":"Implementing surrogate goals for safer bargaining in LLM-based agents","created":"2026-04-06","cited_by_count":0,"area":"agents"},{"id":"2608.20777","title":"Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.28612","title":"InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal","created":"2026-07-21","cited_by_count":0,"area":"agents"},{"id":"2609.00621","title":"Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.03416","title":"Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection","created":"2026-09-03","cited_by_count":0,"area":"agents"}],"next_cursor":null}