Raven：面向可组合智能体的“Harness of Harnesses”开源多智能体生态

View PDF HTML (experimental)

Abstract:As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harness complexity makes manual design difficult to scale, while tighter coupling to specific domains limits the generality of a single harness. The central question thus shifts from how to engineer a stronger harness for one domain to how to autonomously construct specialized harnesses, improve them through experience, and orchestrate them across domains. We introduce Raven, \emph{The Harness of Harnesses}, an open-source multi-agent ecosystem that automatically constructs and evolves modular harnesses for specific models and domains, treating each executable model--harness pair as a composable unit of intelligence. To support an \emph{All-Domain Collaboration Network}, its Host Agent decomposes goals, matches subtasks to specialized agents, coordinates execution dependencies, and integrates results, while a host archive and EverOS preserve experience across tasks and Skill Forge makes that experience available as reusable procedures. Our theory establishes sufficient conditions for such composition to expand reliable task coverage beyond that of the available individual agents under a shared resource budget. On complex and long-horizon tasks, Raven significantly outperforms the state-of-the-art agent systems, pushing the frontier of composable agentic intelligence.

Subjects:	Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Science and Game Theory (cs.GT); Multiagent Systems (cs.MA); Neural and Evolutionary Computing (cs.NE)
Cite as:	arXiv:2609.33439 [cs.AI]
	(or arXiv:2609.33439v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2609.33439 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Dizhan Xue [view email]
[v1] Sun, 27 Sep 2026 10:44:48 UTC (3,056 KB)