Agents

Rules That Govern: A Per-Property Analysis of Multi-Agent LLM Deliberation

Securing the Multi-Chain Ecosystem: A Unified, Agent-Based Framework for Vulnerability Repair in Solidity and Move

HPCAgentTester: A Multi-Agent LLM Approach for Enhanced HPC Unit Test Generation

LLM Reasoning & Code Generation

Investigating how Large Language Models reason, generate code, and can be made more reliable through multi-agent architectures and hallucination mitigation.