Compositional Self-Improvement: Promises and Pitfalls
cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/tldr-pages/tldr
Terminology
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Supervising strong learners by amplifying weak experts
- Decomposed Prompting: A Modular Approach for Solving Complex Tasks
- R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
- h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
- Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
- Distilling System 2 into System 1
- Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
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