Join our daily and weekly newsletters to obtain the latest updates and exclusive content on the coverage of the industry leader. Get more information
Agent interoperability is gaining steam, but continuous organizations continue to propose new interoperability protocols as the industry continues to discover what standards adopt.
A group of researchers from the Carnegie Mellon University proposes a new interoperability protocol that governs the identity, responsibility and ethics of autonomous agents. The orchestration in layers for knowledge agents, or Loka, could join other standards of proposing such as agent 2agent (A2A) and the anthropic model context protocol (MCP).
In an article, the investigators noticed that the emergence of the agents of AI underlines the importance of governing them.
“As your presence expands, the need for a standardized framework to govern your interactions becomes essential,” the researchers wrote. “Despite their growing ubiquity, operating agents within the systems in isolated, which lack a common protocol for communication, ethical reasoning and compliance with jurisdictional regulations. This possess fragmentation, successful gaps.”
To address this, they propose the open source Loka, which would allow agents to prove their identity, “exchange semantically rich ethical messages,” add responsibility and establish the formation of ethical governance through the company.
Loka is based on what researchers refer as a layer of universal agent identity, a framework that assigns agents a unique and verifiable identity.
“We visualize Loka as a fundamental architecture and a call to reexamine the central elements: identity, intention, trust and ethical consensus – the interactions of the shoulder agents. As the reach of the agents of AI expands the infrasure Canti -jeterherti Reversiments This Transition”, Rajeh Ranjan, one of the researchers of the researchers, said Venturebeat.
Loka layers
Loka works like a layer in layers. The first battery revolves around identity, which presents what the agent is. This includes a decentralized identifier or a “unique cryptographic verifiable identification.” This would allow users and other agents to verify the agent’s identity.
The next layer is the communication layer, where the agent informs another agent of his intention and the task he must perform. This is followed by ethics later and the security layer.
Loka’s ethics layer establishes how the agent behaves. It incorporates “a flexible but robust ethical decision -making frame that allows agents to adapt to variable ethical standards that depend on the context in what they operate.” The Loka protocol used collective decision -making models, allowing agents within the framework to determine their next steps and evaluate whether the steps are aligned with ethical and responsible standards.
Meanwhile, the security layer uses what researchers describe as “quantity resistant cryptography.”
What differentiates Loka
The researchers said Loka stands out
Loka could be useful for companies to guarantee the safety of agents that implement in the world and provide a traceable way of understanding how the agent made decisions. A fear of many companies that have an agent will take advantage of another system or access private data and make an error.
Ranjan said the system “highlights the need to define who agents are and how they make decisions and how are responsible heroes.”
“Our vision is to illuminate the critical questions that are often eclipsed in AI agents in scale: how do we create ecosystems where these agents can be reliable, responsible and interoperable ethical heroes in several systems?” Ranjan said.
Loka will have to compete with other protocols and standards of agents that are now emerging. Protocols such as MCP and A2A have found a large audience, not only because the technical solutions they provide, but because process projects are backed by organizations that people know. Anthrope began MCP, while Google supports A2A, and both protocols have gathered many open companies to use and improve these standards.
Loka operates independently, but Ranjan said they received “very encouraging and exciting comments” from other researchers and other institutions to expand the Loka research project.
