Papers by Liuzhenghao Lv

Copied to clipboard

Challenge:	Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs.
Approach:	They propose a framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM) they propose reducing token consumption by 6 through symbolic abstraction to address context bottlenecks .
Outcome:	The proposed framework achieves 95.6% physical compliance, compared to 21.0% for ReAct, in the extended BioProBench benchmark.