6 papers
Effective Harness Engineering for Algorithm Discovery with Coding Agents
Yoichi Ishibashi, Taro Yano, Masafumi Oyamada
AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm discovery. However, discovery s…
Can a Crow Hatch a Falcon? Lineage Matters in Predicting Large Language Model Performance
Takuya Tamura, Taro Yano, Masafumi Enomoto +1
Accurately forecasting the performance of Large Language Models (LLMs) before extensive fine-tuning or merging can substantially reduce both computational expense and development t…
An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability
Yusuke Yamauchi, Taro Yano, Masafumi Oyamada
As large language models (LLMs) continue to advance, reliable evaluation methods are essential particularly for open-ended, instruction-following tasks. LLM-as-a-Judge enables auto…
Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning
Yoichi Ishibashi, Taro Yano, Masafumi Oyamada
Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a fr…
LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents
Taro Yano, Yoichi Ishibashi, Masafumi Oyamada
Large Language Models (LLMs) have demonstrated exceptional performance across a wide range of tasks. To further tailor LLMs to specific domains or applications, post-training techn…
Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning
Yoichi Ishibashi, Taro Yano, Masafumi Oyamada
Large Language Models (LLMs) have demonstrated significant improvements in reasoning capabilities through supervised fine-tuning and reinforcement learning. However, when training…