https://ahren09.github.io/tags/knowledge-distillation/Knowledge DistillationHugo Blox Builder (https://hugoblox.com)en-usWed, 04 Feb 2026 00:00:00 +0000https://ahren09.github.io/media/icon_hu_eee6347cbdb2cc3f.pnghttps://ahren09.github.io/tags/knowledge-distillation/https://ahren09.github.io/publication/neurips26_agentark/Wed, 04 Feb 2026 00:00:00 +0000https://ahren09.github.io/publication/neurips26_agentark/<h2 id="abstract">Abstract</h2> <p>Multi-agent systems achieve strong performance on complex tasks by orchestrating diverse roles, planners, and tool-using agents. However, deploying full multi-agent stacks is expensive and brittle. We introduce AgentArk, a distillation framework that compresses multi-agent intelligence into a single LLM agent. AgentArk decomposes multi-agent trajectories into role-conditioned skills and trains a single agent to reproduce the collaborative behavior of the original ensemble.</p> <h2 id="links">Links</h2> <ul> <li> </li> </ul>