Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists
cs.CL
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- GLM-5: from Vibe Coding to Agentic Engineering
- The Llama 3 Herd of Models
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Unlocking LLM Creativity in Science through Analogical Reasoning
- Gemma 3 Technical Report
- Kimi K3: Open Frontier Intelligence
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
- Qwen3 Technical Report
- Structured Scaling of AI Discovery Across Diverse Scientific Domains
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data