{"total":123,"rows":[{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"id":"2510.11977","title":"Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation","created":"2025-10-13","cited_by_count":92,"area":"agents"},{"id":"2503.00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","created":"2025-02-28","cited_by_count":89,"area":"agents"},{"id":"2506.15740","title":"SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents","created":"2025-06-17","cited_by_count":71,"area":"agents"},{"id":"2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","created":"2025-03-31","cited_by_count":43,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2505.20662","title":"AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2505.11855","title":"When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research","created":"2025-05-17","cited_by_count":26,"area":null},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2504.06260","title":"FEABench: Evaluating Language Models on Multiphysics Reasoning Ability","created":"2025-04-08","cited_by_count":22,"area":"lr"},{"id":"2506.01372","title":"AI Scientists Fail Without Strong Implementation Capability","created":"2025-06-02","cited_by_count":21,"area":null},{"id":"2507.18901","title":"REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?","created":"2025-07-25","cited_by_count":21,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"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":"2606.07591","title":"ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research","created":"2026-05-28","cited_by_count":17,"area":"agents"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15,"area":"agents"},{"id":"2503.01811","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2506.22419","title":"The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements","created":"2025-06-27","cited_by_count":15,"area":null},{"id":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"id":"2510.10909","title":"PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature","created":"2025-10-13","cited_by_count":15,"area":"lr"},{"id":"2511.04583","title":"Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper","created":"2025-11-06","cited_by_count":12,"area":null},{"id":"2601.01678","title":"HeurekaBench: A Benchmarking Framework for AI Co-scientist","created":"2026-01-04","cited_by_count":12,"area":"lr"},{"id":"2510.24591","title":"ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?","created":"2025-10-28","cited_by_count":11,"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":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2603.23749","title":"Efficient Benchmarking of AI Agents","created":"2026-03-24","cited_by_count":10,"area":"agents"},{"id":"2605.19156","title":"How Far Are We From True Auto-Research?","created":"2026-05-18","cited_by_count":10,"area":null},{"id":"2605.23204","title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","created":"2026-05-22","cited_by_count":10,"area":null},{"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":"2607.27191","title":"Can AI agents conduct open-ended AI research? Early evidence from two case studies","created":"2026-07-29","cited_by_count":10,"area":null},{"id":"2506.03231","title":"NetArena: Dynamic Benchmarks for AI Agents in Network Automation","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2602.11354","title":"ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences","created":"2026-02-11","cited_by_count":9,"area":"agents"},{"id":"2605.00803","title":"Can Coding Agents Reproduce Findings in Computational Materials Science?","created":"2026-05-01","cited_by_count":9,"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":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2503.01424","title":"From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems","created":"2025-03-03","cited_by_count":8,"area":null},{"id":"2605.16616","title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2608.14905","title":"How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks","created":"2026-08-14","cited_by_count":8,"area":"agents"},{"id":"2605.13950","title":"Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2605.14892","title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2606.11150","title":"ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity","created":"2026-06-09","cited_by_count":6,"area":"agents"},{"id":"2606.11447","title":"AI Coding Agents Can Reproduce Social Science Findings","created":"2026-06-09","cited_by_count":6,"area":"agents"},{"id":"2509.20374","title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2604.21965","title":"Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results","created":"2026-04-23","cited_by_count":5,"area":"agents"},{"id":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.08561","title":"Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches","created":"2026-02-09","cited_by_count":4,"area":"agents"},{"id":"2606.01961","title":"AutoMedBench: Towards Medical AutoResearch with Agentic AI Models","created":"2026-06-01","cited_by_count":4,"area":"agents"},{"id":"2606.26158","title":"Life After Benchmark Saturation: A Case Study of CORE-Bench","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2606.31551","title":"AutoTrainess: Teaching Language Models to Improve Language Models Autonomously","created":"2026-06-30","cited_by_count":4,"area":"agents"},{"id":"2608.17271","title":"ASI-Bench: At the Dawn of Artificial Superintelligence","created":"2026-08-18","cited_by_count":4,"area":null},{"id":"2609.04280","title":"EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?","created":"2026-09-03","cited_by_count":4,"area":"agents"},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2603.20256","title":"SciNav: A General Agent Framework for Scientific Coding Tasks","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"id":"2604.15664","title":"Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2606.14516","title":"Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2608.00267","title":"LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2507.08038","title":"AblationBench: Evaluating Automated Planning of Ablations in Empirical AI Research","created":"2025-07-09","cited_by_count":2,"area":"agents"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2603.00058","title":"PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2603.17216","title":"ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments","created":"2026-03-17","cited_by_count":2,"area":"agents"},{"id":"2603.30038","title":"Benchmarking PhD-Level Coding in 3D Geometric Computer Vision","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.04074","title":"FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2604.12198","title":"Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers","created":"2026-04-14","cited_by_count":2,"area":"agents"},{"id":"2605.28371","title":"From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence","created":"2026-05-27","cited_by_count":2,"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":"2607.02931","title":"VERITAS: Towards a General-Purpose Replication Tool for Scientific Research","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2607.10522","title":"Towards Autonomous and Auditable Medical Imaging Model Development","created":"2026-07-12","cited_by_count":2,"area":null},{"id":"2608.13060","title":"VALG: An Agentic System for ML Theory Research","created":"2026-08-13","cited_by_count":2,"area":"agents"},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2609.11117","title":"Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Papers","created":"2026-09-10","cited_by_count":2,"area":"agents"},{"id":"2601.13545","title":"TruthTensor: Evaluating LLMs through Human Imitation on Prediction Market under Drift and Holistic Reasoning","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2603.20667","title":"REVERE: Reflective Evolving Research Engineer","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.13201","title":"InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2605.12808","title":"Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse","created":"2026-05-12","cited_by_count":1,"area":"agents"},{"id":"2606.02006","title":"An Agentic Approach Towards Replication Package Quality Evaluation","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2607.02134","title":"Coding-agents can replicate scientific machine learning papers","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.10569","title":"When Does Restricting a Coding Agent to execute_code Help? A Regime $\\times$ Agent-Design Ablation","created":"2026-07-12","cited_by_count":1,"area":"agents"},{"id":"2607.27518","title":"Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.24252","title":"SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2608.24291","title":"ReproAgent: Contract-Guided Paper-to-Code Reproduction","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2608.24979","title":"FrontierChallenge: Evaluating Scientific Workflow Completion","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.05079","title":"TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2601.06158","title":"PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.09753","title":"Critically Engaged Pragmatism: Scientific Norm and Social, Pragmatist Epistemology for AI Science Evaluation Tools","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.14429","title":"Measuring the State of Open Science in Transportation Using Large Language Models","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.11270","title":"Evaluating LLM Agents on Automated Software Analysis Tasks","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2604.19606","title":"AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.16902","title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.24081","title":"PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.12113","title":"Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.07743","title":"QuantumMind: Constraint-Grounded Agentic Reasoning for Speedup Analysis in Quantum Computing","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.09537","title":"verdi: retrieval is not transfer for continual world model optimization","created":"2026-08-10","cited_by_count":0,"area":"wm"}],"next_cursor":"100"}