5 papers
EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts
Yiming Lu, Sihang Zeng, Zhengxu Tang +3
Epidemic LLM forecasters are usually trained and evaluated as static supervised models, whereas operational pandemic forecasting is a streaming process in which labels arrive after…
Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication
Yiming Lu, Xun Wang, Simin Ma +6
Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a f…
DeFine: Decision-Making with Analogical Reasoning over Factor Profiles
Yebowen Hu, Xiaoyang Wang, Wenlin Yao +5
LLMs are ideal for decision-making thanks to their ability to reason over long contexts. However, challenges arise when processing speech transcripts that describe complex scenario…
Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic
Haoming Li, Zhaoliang Chen, Songyuan Liu +2
In this work, we provide a systematic analysis of how large language models (LLMs) contribute to solving planning problems. In particular, we examine how LLMs perform when they are…
STRUX: An LLM for Decision-Making with Structured Explanations
Yiming Lu, Yebowen Hu, Hassan Foroosh +2
Countless decisions shape our daily lives, and it is paramount to understand the how and why behind these choices. In this paper, we introduce a new LLM decision-making framework c…