No Second Run: Does RSI Stop at Frontier Pre-training?
cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/GAIR-NLP/801-30B
Terminology
Sources
- SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
- Chinchilla Scaling: A replication attempt
- PIQA: Reasoning about Physical Commonsense in Natural Language
- Evaluating Large Language Models Trained on Code
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization
- daVinci-Env: Open SWE Environment Synthesis at Scale
- AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
- RSI Arena: Towards Recursive Self-Improvement with Human Feedback
- daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Muon is Scalable for LLM Training
- SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
- AutoData: Agentic Search for Pre-training Data Selection
- Data Darwinism Part II: DataEvolve -- AI can Autonomously Evolve Pretraining Data Curation
- KernelBench: Can LLMs Write Efficient GPU Kernels?
- Training Software Engineering Agents and Verifiers with SWE-Gym
- Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents