4 papers
ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence
Yiwei Chen, Amila Weerasinghe, Siddharth Biswal +4
Large language models are increasingly used as scientific assistants, yet we still lack reliable ways to evaluate whether they can investigate a system rather than merely answer a…
Zephyrus: An Agentic Framework for Weather Science
Sumanth Varambally, Marshall Fisher, Jas Thakker +14
Foundation models for weather science are pre-trained on vast amounts of structured numerical data and outperform traditional weather forecasting systems. However, these models lac…
Crossword: Adaptive Consensus for Dynamic Data-Heavy Workloads
Guanzhou Hu, Yiwei Chen, Andrea Arpaci-Dusseau +1
We present Crossword, a flexible consensus protocol for dynamic data-heavy workloads, a rising challenge in the cloud where replication payload sizes span a wide spectrum and intro…
Retrospective Learning from Interactions
Zizhao Chen, Mustafa Omer Gul, Yiwei Chen +3
Multi-turn interactions between large language models (LLMs) and users naturally include implicit feedback signals. If an LLM responds in an unexpected way to an instruction, the u…