Aim: to provide agents with human-like cognitive skills such as memory, perception, natural language, learning.
Natural Language Skills
One particularly interesting idea to increase both the reasoning and interaction skills of GOAL agents at the same time is to provide GOAL agents with natural language skills. The basic idea would be to provide GOAL agents with a computational semantics for interpreting natural language in a particular domain. Natural language skills would allow agents to more easily interact with humans which is useful in a range of contexts (call centers, internet, e.g. shopping assistants, games, etc.). The challenge is to outperform what has been achieved already in classic domains such as the Blocks World which is quite well-behaved (a classic and very famous reference is SHRDLU of Terry Winograd).
Theory of Mind
Providing GOAL Agents with a Theory of Mind: The reasoning skills of a BDI agent are particularly important and can be extended in various ways. One important extensions concerns agents that are able to reason about other agents. That would agents allow to infer the needs of other agents and to predict what other agents will do. In psychology such skills have been studied under the umbrella term Theory of Mind and the challenge would be to develop similar human skills for interacting with other humans.
Norling and Ritter, 2004 propose CoJack? as an agent-based architecture.
High-Level Behaviour-Representation Languages and Agent Programming Languages
Various high-level behaviour representation languages have been proposed that abstract from the details of some of the cognitive modeling programming languages for existing architectures such as Soar and ACT-R. Examples of such languages include the High Level Symbolic Representation (HLSR) language and Herbal.