Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents
Qi Li, Jianjun Xu, Pingtao Wei +8
With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deploy…
cs.AI2025
Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation
Shaonan Wu, Shuai Lu, Yeyun Gong +2
Formal proofs are challenging to write even for experienced experts. Recent progress in Neural Theorem Proving (NTP) shows promise in expediting this process. However, the formal c…