← NSFGrants
HomeNsf Awards

CAREER: Adaptive Knowledge Synthesis for Language Model Reasoning — NSF Award to Washington University (MO, $417,565)

Large Language Models (LLMs) have shown impressive performance on pure reasoning tasks like math questions and logic puzzles. However, Artificial Intelligent (AI) systems with such LLMs still struggle with complex tasks that require finding and combining information from multiple external sources. For instance, answeri

Award titleCAREER: Adaptive Knowledge Synthesis for Language Model Reasoning
Award ID2541822
AwardeeWashington University
CitySAINT LOUIS
StateMO
Amount obligated$417,565
Principal investigatorJiaxin Huang
ProgramInfo Integration & Informatics
Start date10/01/2026
AbstractLarge Language Models (LLMs) have shown impressive performance on pure reasoning tasks like math questions and logic puzzles. However, Artificial Intelligent (AI) systems with such LLMs still struggle with complex tasks that require finding and combining information from multiple external sources. For instance, answering a complicated legal or scientific question often requires a step-by-step investigation where the answer to one question determines what to search for next. While current AI syst
SourceNSF Awards

🔍 Search all NSF awards →