Author of "ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory" on arXiv
How media typically covers I-Hung Hsu
I-Hung Hsu as author
Google researchers introduce Supervised Reinforcement Learning (SRL), a training framework that enables 7B parameter models to achieve better multi-step reasoning by providing step-wise reward signals based on expert action similarity rather than token-by-token imitation.
“Author of "Google Researchers Show SRL Gives 7B Models Better Structured Reasoning by Rewar" on arXiv”
ReasoningBank, a memory framework that enables LLM agents to learn from accumulated interaction history and self-evolve through reasoning strategies, outperforms existing memory mechanisms on web browsing and software engineering tasks.
“Author of "ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory" on arXiv”