Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
cs.AI, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: Accepted at NeurIPS 2026
Code: https://github.com/bilemond/ChemDiffAgent
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation
- Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems
- rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Mercury: Ultra-Fast Language Models Based on Diffusion
- OpenAI o1 System Card
- Language models in molecular discovery
- MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
- Decoupled Weight Decay Regularization
- Improve Mathematical Reasoning in Language Models by Automated Process Supervision
- Concrete Score Matching: Generalized Score Matching for Discrete Data
- Large Language Diffusion Models
- Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
- A Review of Large Language Models and Autonomous Agents in Chemistry
- S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research
- CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning
- From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
- ReAct: Synergizing Reasoning and Acting in Language Models
- Dream 7B: Diffusion Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems