most citedCheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing

Wanli Cheng, Haiya Xiang, Juntao Li +2

Large Reasoning Models (LRMs) achieve strong reasoning capabilities, yet long-chain reasoning becomes inefficient once the intermediate answer stabilizes across reasoning steps: ad…