Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem – Machine Learning Blog | ML@CMU | Carnegie Mellon University
Figure 1: Training models to optimize test-time compute and learn "how to discover" correct responses, as opposed to the traditional learning paradigm of learning "what answer" to output. The major strategy to improve large language models (LLMs) thus far has been to use more and more high-qualit
Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem – Machine Learning Blog | ML@CMU | Carnegie Mellon University --> Input your search keywords and press Enter. Categories: Research Educational Categories: Research Educational machine learning Research Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem Authors Amrith Setlur by Amrith Setlur --> Affiliations Published January 8, 2025 DOI Figure 1 : Training models to optimize test-time compute and learn “how to discover” correct responses, as opposed to the traditional learning paradigm of lea
saved by
related reading
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
- How can LLM RL Work Despite Information-Theoretic Inefficiencyberen.io
- State of RL for reasoning LLMs | A. Weersaweers.de
- IsoCompute Playbook: Optimally Scaling Sampling Compute for RL Training of LLMscompute-optimal-rl-llm-scaling.github.io
- [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
- How to Explore to Scale RL Training of LLMs on Hard Problems? – Machine Learning Blog | ML@CMU | Carnegie Mellon Universityblog.ml.cmu.edu
- Self-Adapting Language Modelsarxiv.org
- [2606.07527] Post-training is (Massive) Supervised Learningarxiv.org
- Language Models can Solve Computer Tasksarxiv.org
- Transformers Inference Optimization Toolset | AstraBlogastralord.github.io
- [2602.19362] LLMs Can Learn to Reason Via Off-Policy RLarxiv.org
- [2605.12484] Learning, Fast and Slow: Towards LLMs That Adapt Continuallyarxiv.org