← Back to all news
arXiv AI By Mengdi Liu, Chenghao Jia, Hong Chang, Shiguang Shan

Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning

Read the original on arXiv AI →

The paper introduces ChemDiffAgent, a masked diffusion language agent designed for tool‑integrated chemical reasoning. Unlike traditional autoregressive agents, it treats reasoning as iterative denoising over interleaved reasoning and tool‑use trajectories, allowing joint decision making under full‑trajectory context. A two‑stage post‑training framework further refines tool use and reasoning, and the authors benchmark the model on six chemistry tasks, reporting a ~20% performance gain over autoregressive baselines and competitive results against larger models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 3

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

arXiv:2602. 07075v5 Announce Type: replace-cross Abstract: Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems.

By Xinwu Ye, Yicheng Mao, Yuxuan Liao, Jia Zhang, Yimeng Liu, Li Hao, Fang Wu, Zhiwei Li, Zehong Wang, Zhiyuan Liu, Zhenfei Yin, Li Yuan, Philip Torr, Huan Sun, xiangxiang Zeng, Mengdi Wang, Le Cong, Shenghua Gao, Xiangru Tang
llmsbenchmarks
More like this →
arXiv AI
Sep 18

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

oMeBench is a large-scale, expert-curated benchmark designed to evaluate large language models (LLMs) on organic mechanism reasoning. It contains over 10,000 annotated mechanistic steps, including reaction type labels, intermediate structures, and difficulty ratings, and introduces the oMeS scoring framework to assess logical consistency and chemical structural similarity. Evaluation shows that while current LLMs display promising chemical intuition, they often fail to produce correct and consistent multi-step reasoning, though prompting and fine-tuning can bring smaller models up to the level of closed‑source frontier models.

By Ruiling Xu, Yifan Zhang
llmsfine-tuningbenchmarks
More like this →