2 papers
cs.AI2026
SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
Ha Minh Hieu, Tongyao Zhu, Do Xuan Long +1
LLM-driven evolutionary search is a promising paradigm for scientific discovery, but existing methods remain costly and slow, often applying expensive reasoning uniformly while und…
cs.CL2026
Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs
Vu Duc Anh, Nhat M. Hoang, Do Xuan Long +3
Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs). In this work, we propose…