4 citations · 5 across the 4 of their papers we have counts for
5 papers · 1 filter
ChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning
Aotian Chen, Frazier N. Baker, Reza Averly +5
Current chemistry benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an observed chemical effect occur…
MADDIE: Multi-Agent Drug Discovery Engine
Ye Liu, Reza Averly, Avery Meyer +4
Drug discovery remains a resource-intensive and time-consuming process, involving billions of dollars and a decade of development to advance a drug to market. While many in silico…
FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification
Botao Yu, Bo Zhou, Daniel Adu-Ampratwum +7
As generative models and AI agents propose chemical reactions at a scale beyond expert review, feasibility verifiers decide which proposals enter synthesis planning. But do their d…
MMORF: A Multi-agent Framework for Designing Multi-objective Retrosynthesis Planning Systems
Frazier N. Baker, Trieu Nguyen, Reza Averly +4
Multi-objective retrosynthesis planning is a critical chemistry task requiring dynamic balancing of quality, safety, and cost objectives. Language model-based multi-agent systems (…
Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation
Xinyi Ling, Ye Liu, Reza Averly +1
Goal-oriented conversational systems require making sequential decisions under uncertainty about the user's intent, where the algorithm must balance information acquisition and tar…