{"total":40,"rows":[{"id":"2504.08066","title":"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search","created":"2025-04-10","cited_by_count":422,"area":"agents"},{"id":"2506.11763","title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","created":"2025-06-13","cited_by_count":248,"area":"agents"},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2507.15550","title":"PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors","created":"2025-07-21","cited_by_count":15,"area":"agents"},{"id":"2510.01285","title":"LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science","created":"2025-09-30","cited_by_count":15,"area":"agents"},{"id":"2604.24955","title":"BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks","created":"2026-04-27","cited_by_count":15,"area":"agents"},{"id":"2603.11076","title":"DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use","created":"2026-03-10","cited_by_count":13,"area":"agents"},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"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":"2601.21800","title":"BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics","created":"2026-01-29","cited_by_count":10,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2605.24002","title":"Harnessing AtomisticSkills for Agentic Atomistic Research","created":"2026-05-18","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":"2608.25286","title":"BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks","created":"2026-08-26","cited_by_count":5,"area":"agents"},{"id":"2605.08941","title":"MDGYM: Benchmarking AI Agents on Molecular Simulations","created":"2026-05-09","cited_by_count":4,"area":"agents"},{"id":"2605.21740","title":"SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?","created":"2026-05-20","cited_by_count":4,"area":"agents"},{"id":"2512.17838","title":"ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challenges","created":"2025-12-19","cited_by_count":3,"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":"2604.14004","title":"Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents","created":"2026-04-15","cited_by_count":3,"area":"agents"},{"id":"2605.10876","title":"AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2508.13201","title":"Benchmarking LLM-based agents for single-cell omics analysis","created":"2025-08-16","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":"2603.28986","title":"Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research","created":"2026-03-30","cited_by_count":1,"area":"agents"},{"id":"2606.13602","title":"EpiBench: Verifiable Evaluation of AI Agents on Epigenomics Analysis","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2606.19245","title":"TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2606.19899","title":"Measuring Biological Capabilities and Risks of AI Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2605.05985","title":"BioResearcher: Scenario-Guided Multi-Agent for Translational Medicine","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.06177","title":"BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2606.20839","title":"Process-Reward Tactic Evolution for Long-Horizon Bioinformatics Workflows","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2607.23975","title":"Plato-Bio: verification-first biological novelty screening with temporal rediscovery and structural benchmarks","created":"2026-07-27","cited_by_count":0,"area":"agents"},{"id":"2607.26155","title":"ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2607.27556","title":"Evaluating Agentic Bioinformatics through Function, Evidence, and Validation","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2609.03871","title":"Bioinfoysis Technical Report","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"id":"2609.34274","title":"BIABench: Evaluating AI agents on real-world bioimage analysis tasks","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.04740","title":"Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.13116","title":"DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14393","title":"SciCurateBench: Curating Experimental Data from Heterogeneous Scientific Literature with Verbal-Action Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14683","title":"Triage-PiEvo: Evidence Admission for Principle-Evolving Scientific Agents","created":"2026-10-10","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}