Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines
Prabhjot Singh, Bhushan Pawar
Sequential multi-agent LLM pipelines chain specialized agents without verification at handoffs, creating a structural flaw with measurable and severe consequences. We show that hal…
cs.AI2026
DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification
Mohammed Yousif, Prabhjot Singh, Arjun Pankajakshan +1
Real-world document classification pipelines typically apply the same sequence of models to every incoming document, regardless of its complexity or type. This leads to inefficient…