Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search
cs.LG
Submitted: 2026-08-16
Updated: 2026-08-30
Code: https://github.com/karpathy/autoresearch
Terminology
Sources
- LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization
- Natural Language Reinforcement Learning
- A Tutorial on Bayesian Optimization
- AntBO: Towards Real-World Automated Antibody Design with Combinatorial Bayesian Optimisation
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Bayesian Optimization of Catalysis With In-Context Learning
- Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Learning Stateful Predictive Knowledge From Experience
- PaperBench: Evaluating AI's Ability to Replicate AI Research
- AI Research Agents Narrow Scientific Exploration
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
- ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
- ReAct: Synergizing Reasoning and Acting in Language Models
- Diffusion Large Language Models for Black-Box Optimization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks