ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine
cs.AI, cs.CL
Submitted: 2026-10-03
Updated: 2026-10-03
Sources
- Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents
- Accelerating scientific discovery with Co-Scientist
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Anchorless Diversification for Parallel LLM Ideation
- AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery
- Examining and Addressing Barriers to Diversity in LLM-Generated Ideas
- Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents
- DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations
- Towards Execution-Grounded Automated AI Research
- Towards Diverse Scientific Hypothesis Search with Large Language Models
- EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
- EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery
- Training AI Scientists to Replicate Research
- Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
- Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
- HindSight: Evaluating LLM-Generated Research Ideas via Future Impact
- Large Language Models can Learn Rules
- Hypothesis Generation with Large Language Models
- IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
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