Region
national
Partners
1 partner
Phase
OngoingStart
Jan 01, 2026
End
Jan 01, 2027
Timeline
No timeline events available yet.
Abstract
Adobe’s Learning Funds supports PhD research that advances state-of-the-art intelligent systems. This grant aims to fund doctoral research at **UTCN** focused on multi-agent systems for collaboration and orchestration, with the goal of improving how multiple autonomous agents coordinate, share knowledge, and synthesize their outputs into high-quality responses for end users.
Adobe–UTCN PhD Collaboration
Adobe’s Learning Funds supports PhD research that advances state-of-the-art intelligent systems. This grant aims to fund doctoral research at UTCN focused on multi-agent systems for collaboration and orchestration, with the goal of improving how multiple autonomous agents coordinate, share knowledge, and synthesize their outputs into high-quality responses for end users.
Research Focus
The research will investigate techniques for:
- Agent Communication
- Decision Coordination
- Conflict Resolution
- Result Aggregation
These strategies aim to enable more reliable, transparent, and context-aware final answers derived from diverse agent perspectives.
Grant Details
- Duration: One year, with the possibility of renewal based on research progress and outcomes.
Agents for Goal Oriented Discourse
This project investigates the development of multi-agent dialogue systems capable of sustaining coher- ent and goal-directed discourse. While existing conversational AI systems primarily support single- agent or single-user interactions, emerging applications increasingly require multiple agents—human and artificial—to coordinate through extended, structured dialogue. The research will focus on modeling discourse dynamics across agents, including turn-taking, con- text management, speaker roles, and dialogue structure. Methods will integrate statistical dialogue modeling, structured planning, and multi-agent coordination. Particular attention will be given to discourse-aware reasoning and the role of language in collaborative task execution, with the goal of enabling agents to engage in structured, purposeful interaction that remains interpretable and contextually grounded over time.