# Predicting Empirical AI Research Outcomes with Language Models

arXiv: https://arxiv.org/abs/2506.00794 · HTML: https://mlsanity.com/paper/2506.00794/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 19 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities](https://mlsanity.com/paper/2409.19839/) (2024)
- [Approaching Human-Level Forecasting with Language Models](https://mlsanity.com/paper/2402.18563/) (2024)
- [Large language models surpass human experts in predicting neuroscience results](https://mlsanity.com/paper/2403.03230/) (2024)
- [Forecasting Future World Events with Neural Networks](https://mlsanity.com/paper/2206.15474/) (2022)
- [LitLLM: A Toolkit for Scientific Literature Review](https://mlsanity.com/paper/2402.01788/) (2024)
- [Goal Driven Discovery of Distributional Differences via Language Descriptions](https://mlsanity.com/paper/2302.14233/) (2023)
- [Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament](https://mlsanity.com/paper/2310.13014/) (2023)
- [Humans vs Large Language Models: Judgmental Forecasting in an Era of Advanced AI](https://mlsanity.com/paper/2312.06941/) (2023)

## Built on by (most cited first, 17 of 17)

- [ScholarEval: Research Idea Evaluation Grounded in Literature](https://mlsanity.com/paper/2510.16234/) (2025)
- [Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas](https://mlsanity.com/paper/2603.10303/) (2026)
- [Measuring AI R&D Automation](https://mlsanity.com/paper/2603.03992/) (2026)
- [Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts](https://mlsanity.com/paper/2507.19477/) (2025)
- [Automated Researchers Can Mitigate Well-characterized Alignment Failures](https://mlsanity.com/paper/2608.28945/) (2026)
- [Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions](https://mlsanity.com/paper/2509.20645/) (2025)
- [When AI reviews science: Can we trust the referee?](https://mlsanity.com/paper/2604.23593/) (2026)
- [Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation](https://mlsanity.com/paper/2605.21491/) (2026)
- [What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation](https://mlsanity.com/paper/2608.22948/) (2026)
- [DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation](https://mlsanity.com/paper/2609.22104/) (2026)
- [What if automating AI R&D triggers an intelligence explosion?](https://mlsanity.com/paper/2609.36054/) (2026)
- [The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks](https://mlsanity.com/paper/2609.25804/) (2026)
- [Alignment Forecasting: Predicting Misalignment From Training Data](https://mlsanity.com/paper/2609.35805/) (2026)
- [Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts](https://mlsanity.com/paper/2610.00314/) (2026)
- [IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation](https://mlsanity.com/paper/2610.04074/) (2026)
- [PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution](https://mlsanity.com/paper/2610.04737/) (2026)
- [Language Models as AI Research World Models](https://mlsanity.com/paper/2610.12235/) (2026)

## Abstract (arXiv)

Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even expert researchers can only acquire through substantial experience. We build the first benchmark for this task and compare LMs with human experts. Concretely, given two research ideas (e.g., two jailbreaking methods), we aim to predict which will perform better on a set of benchmarks. We scrape ideas and experimental results from conference papers, yielding 1,585 human-verified idea pairs published after our base model's cut-off date for testing, and 6,000 pairs for training. We then develop a system that combines a fine-tuned GPT-4.1 with a paper retrieval agent, and we recruit 25 human experts to compare with. In the NLP domain, our system beats human experts by a large margin (64.4% v.s. 48.9%). On the full test set, our system achieves 77% accuracy, while off-the-shelf frontier LMs like o3 perform no better than random guessing, even with the same retrieval augmentation. We verify that our system does not exploit superficial features like idea complexity through extensive human-written and LM-designed robustness tests. Finally, we evaluate our system on unpublished novel ideas, including ideas generated by an AI ideation agent. Our system achieves 63.6% accuracy, demonstrating its potential as a reward model for improving idea generation models. Altogether, our results outline a promising new direction for LMs to accelerate empirical AI research.