4 papers
Scaling Test-Time Compute for Agentic Coding
Joongwon Kim, Wannan Yang, Kelvin Niu +13
Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ran…
Prompt Curriculum Learning for Efficient LLM Post-Training
Zhaolin Gao, Joongwon Kim, Wen Sun +4
We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-…
ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context
Joongwon Kim, Anirudh Goyal, Liang Tan +3
We introduce ASTRO, the "Autoregressive Search-Taught Reasoner", a framework for training language models to reason like search algorithms, explicitly leveraging self-reflection, b…
A Systematic Examination of Preference Learning through the Lens of Instruction-Following
Joongwon Kim, Anirudh Goyal, Aston Zhang +6
Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In…