Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning
Jie Liang, Zhengxin Yu, Hamid Nasiri +1
LLM agents need to sustain goal-consistent reasoning across long multi-turn interactions under strict resource constraints. However, as the multi-turn context accumulates, it can d…
cs.LG2026
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan
Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominantly rely o…