From the 1 of 4 linked papers with an AI index.
4 papers
RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
Yanqiao Zhu, Jingru Gan, Xiaoqi Sun +8
RetroAgent is an LLM-based agent that uses structured memory to integrate symbolic search and neural reasoning for multi-step retrosynthesis planning, enabling informed decisions a…
RPO: Decoupling Rollout and Inference Policies for LLM Reasoning
Jingchu Wang, Bingbing Xu, Yige Yuan +4
Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference respon…
ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions
Yue Huang, Zhengzhe Jiang, Xiaonan Luo +12
Empowering large language models (LLMs) with chemical intelligence remains a challenge due to the scarcity of high-quality, domain-specific instruction-response datasets and the mi…
ASKCOS: an open source software suite for synthesis planning
Zhengkai Tu, Sourabh J. Choure, Mun Hong Fong +16
The advancement of machine learning and the availability of large-scale reaction datasets have accelerated the development of data-driven models for computer-aided synthesis planni…