{"total":60,"rows":[{"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":"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":"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":"2603.23749","title":"Efficient Benchmarking of AI Agents","created":"2026-03-24","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":"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":"2608.14905","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":"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":"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":"2606.31551","title":"AutoTrainess: Teaching Language Models to Improve Language Models Autonomously","created":"2026-06-30","cited_by_count":4,"area":"agents"},{"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":"2603.20256","title":"SciNav: A General Agent Framework for Scientific Coding Tasks","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"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":"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":"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":"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":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"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":"2607.10569","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":"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":"2604.11270","title":"Evaluating LLM Agents on Automated Software Analysis Tasks","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"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":"2608.18508","title":"Science Done on a Machine by a Machine: AI Agents in Computational Chemistry","created":"2026-08-19","cited_by_count":0,"area":"agents"},{"id":"2608.23104","title":"Molecular LLM Agents: From Architectural Design to Scientific Autonomy","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2609.16995","title":"PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress","created":"2026-09-15","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":"2609.32213","title":"HM-ROUTER: Joint Model and Harness Routing for Agentic Systems","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.36161","title":"From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.00636","title":"CompMat-Bench: Benchmarking AI Agents for Computational Materials Science","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00651","title":"Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.09944","title":"AgentTime: Can Agents Estimate and Control Their Own Runtime?","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.19507","title":"Structure Before Intelligence: Gating What Agentic Scientific Workflows Release","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}