Collaborating Authors

Open Agent Architecture (OAA)

AITopics Original Links

In a distributed agent framework, we conceptualize a dynamic community of agents, where multiple agents contribute services to the community. When external services or information are required by a given agent, instead of calling a known subroutine or asking a specific agent to perform a task, the agent submits a high-level expression describing the needs and attributes of the request to a specialized Facilitator agent. The Facilitator agent will make decisions about which agents are available and capable of handling sub-parts of the request, and will manage all agent interactions required to handle the complex query. Such a distributed agent architecture allows the construction of systems that are more flexible and adaptable than distributed object frameworks. Individual agents can be dynamically added to the community, extending the functionality that the agent community can provide as a whole.

The Latest: Suspect in Shooting ATF Agent Appears in Court

U.S. News

If convicted, he faces up to 20 years in prison. The ATF agent was shot in the face and is expected to make a full recovery.

Border agents help injured Mexican trying to cross into US illegally

FOX News

President of National Border Patrol Council Brandon Judd explains on'Fox & Friends First.'

Generalizing Multi-Agent Path Finding for Heterogeneous Agents

AAAI Conferences

Multi-Agent Path Finding (MAPF) is the problem of finding non-colliding paths for multiple agents. The classical problem assumes that all agents are homogeneous, with a fixed size and behavior. However, in reality agents are heterogeneous, with different sizes and behaviors. In this paper, we generalize MAPF to G-MAPF for the case of heterogeneous agents. We then show how two previous settings of large agents and k-robust agents are special cases of G-MAPF. Finally, we introduce G-CBS, a variant of the Conflict-Based Search (CBS) algorithm for G-MAPF, which does not cause significant extra overhead.

Can Artificial Intelligence Master the Art of the Deal?


A bot might someday take your job, but perhaps it can help you negotiate a nice severance package, too. A recent research paper (PDF) suggests that AI agents could do all sorts of useful haggling, providing they become a little bit smarter, and users can be persuaded to trust them. The authors envision a world where an AI agent negotiates on your behalf, like buying a house or working out the details of a pay raise. And they write that such technology could allow negotiations in new areas like figuring out the terms of an energy-sharing deal with your neighbor, or the amount of money you should receive for giving up some privacy information to a mobile app. The team has experimented with an Android app that lets you do just that, in fact.