2 papers
cs.AI2025
PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs
Venkat Margapuri, Garik Kazanjian, Naren Kosaraju
Large Language Models (LLMs) often struggle with maintaining coherent multi-step reasoning traces, particularly in tasks that require a structured logical flow. This work introduce…
cs.RO2025
Hybrid Safety Verification of Multi-Agent Systems using -Weighted CBFs and PAC Guarantees
Venkat Margapuri, Garik Kazanjian, Naren Kosaraju
This study proposes a hybrid safety verification framework for closed-loop multi-agent systems under bounded stochastic disturbances. The proposed approach augments control barrier…