Third Eye: Beyond Immediate Gains in Recursive Self-Improvement
cs.LG, cs.AI
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Program Synthesis with Large Language Models
- Accounting for Variance in Machine Learning Benchmarks
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- QLoRA: Efficient Finetuning of Quantized LLMs
- The Llama 3 Herd of Models
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- LoRA: Low-Rank Adaptation of Large Language Models
- Large Language Models Can Self-Improve
- Large Language Models Cannot Self-Correct Reasoning Yet
- Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch
- Overcoming catastrophic forgetting in neural networks
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- Let's Verify Step by Step
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- Target-Independent Micro-Interventions for Predicting Training Response Across Language-Model Families
- Gradient Episodic Memory for Continual Learning
- An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
- TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis