COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learning
COGTRL is proposed, a trajectory-level reinforcement learning framework that trains LLMs to emulate cognitively grounded reasoning by jointly optimizing cognitive traces and the scientific steps produced in an interleaved manner.
Shrinidhi Kumbhar, Santosh Mashetty, Divij Handa et al.
· 1 citation