Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station

arXiv:2610.08927 · cs.AI, cs.MA · Submitted 2026-10-06 · Read on arXiv

cs.AI, cs.MA

Submitted: 2026-10-06

Updated: 2026-10-06

Code: https://github.com/dualverse-ai/station-open-reseach

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes

Sources

• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• The Station: An Open-World Environment for AI-Driven Discovery
• The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
• Can AI agents conduct open-ended AI research? Early evidence from two case studies
• Kosmos: An AI Scientist for Autonomous Discovery
• Accelerating Scientific Research with Gemini in the Real-World
• Subliminal Learning is a LoRA Artifact
• FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
• AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Qwen3-VL Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems