3 papers
cs.LG2025
LeanAgent: Lifelong Learning for Formal Theorem Proving
Adarsh Kumarappan, Mo Tiwari, Peiyang Song +3
Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existi…
cs.LG2024
CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
Donghyun Lee, Je-Yong Lee, Genghan Zhang +2
Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate th…
cs.MA2024
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Donghyun Lee, Mo Tiwari
As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on…