2.1k citations · 6k across the 29 of their papers we have counts for
6 papers · 1 filter
Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks
Yu Jiang, Yue Huang, Hang Hua +6
Long-horizon terminal tasks are used to evaluate and train agents. Human-curated datasets are scarce, so many synthesis methods have emerged. They usually measure the length of a t…
CLORE: Content-Level Optimization for Reasoning Efficiency
Yuyang Wu, Qiyao Xue, Guanxing Lu +4
Reinforcement learning post-training has improved the reasoning ability of large language models, but often produces unnecessarily long, repetitive, or semantically opaque reasonin…
Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
Yuyang Wu, Yue Huang, Shuaike Shen +8
Large Language Models (LLMs) have become increasingly capable as tool-using agents, with benchmarks spanning diverse general agentic tasks. Yet rigorous evaluation of scientific to…
The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS)
Andrew Ferguson, Marisa LaFleur, Lars Ruthotto +97
This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 w…
Simulation Intelligence: Towards a New Generation of Scientific Methods
Alexander Lavin, David Krakauer, Hector Zenil +21
The original "Seven Motifs" set forth a roadmap of essential methods for the field of scientific computing, where a motif is an algorithmic method that captures a pattern of comput…
Deep Reinforcement Learning for De-Novo Drug Design
Mariya Popova, Olexandr Isayev, Alexander Tropsha
We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep an…