2 papers
cs.AI2026
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Pengcheng Jiang, Zhiyi Shi, Kelly Hong +5
Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which c…
cs.AI2025
How GPT learns layer by layer
Jason Du, Kelly Hong, Alishba Imran +3
Large Language Models (LLMs) excel at tasks like language processing, strategy games, and reasoning but struggle to build generalizable internal representations essential for adapt…