{"total":14,"rows":[{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2505.07889","title":"BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science","created":"2025-05-11","cited_by_count":16,"area":"lr"},{"id":"2601.01678","title":"HeurekaBench: A Benchmarking Framework for AI Co-scientist","created":"2026-01-04","cited_by_count":12,"area":"lr"},{"id":"2605.26087","title":"DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking","created":"2026-05-25","cited_by_count":10,"area":"lr"},{"id":"2511.20490","title":"MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology","created":"2025-11-25","cited_by_count":6,"area":"lr"},{"id":"2504.11364","title":"Offline Learning and Forgetting for Reasoning with Large Language Models","created":"2025-04-15","cited_by_count":4,"area":"lr"},{"id":"2602.11609","title":"scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2510.11985","title":"CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2602.08948","title":"CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2510.05335","title":"Biomedical reasoning in action: Multi-agent System for Auditable Biomedical Evidence Synthesis","created":"2025-10-06","cited_by_count":0,"area":"lr"},{"id":"2607.13220","title":"Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2608.23898","title":"BenchBench-Protocol: Evaluating Real-World Wet-Lab Protocol Reasoning and Modification","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.34537","title":"The Marathon of Scientific Reasoning: Robustness of Scientific Agents to Perturbations in Multi-Turn Interactions","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.04915","title":"Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}