Tagged articles
openJiuwen
10 articles · Page 1 of 1
Huawei's openJiuwen team introduces Jiuwen Symbiosis, a physical agent system that uses a perception-planning-execution-feedback loop, execution memory, and safety guardrails to dynamically orchestrate heterogeneous lab equipment, enabling AI-designed experiments to run reliably in automated wet labs.
agent loopexecution memoryheterogeneous devices
0 likes · 14 min read

In a two-hour hackathon, freshman students with no prior project experience used Huawei's AI Shell, CodeArts, and openJiuwen to build four functional AI-powered applications—posture monitoring, fatigue detection, task management, and health reminders—demonstrating how pre-configured AI development tools lower entry barriers for beginners.
AI applicationsAI-assisted developmentCodeArts
0 likes · 6 min read

NTU researchers evaluated four configurable harnesses across five models and three benchmarks, finding harness performance depends on specific model-harness-task combinations rather than fixed rankings, with native harnesses not always optimal and cost not correlating with performance.
AI agentsAgent EvaluationAgent Harness
0 likes · 19 min read

openJiuwen WorkSwarm introduces a full-duplex multimodal AI agent platform where a real-time model handles live audio/video interaction while a Core Agent executes complex tasks in the background, allowing users to interrupt, reprioritize, and continue chatting without waiting for tool calls to finish.
Ascend NPUbackground task executionfull-duplex
0 likes · 11 min read

openJiuwen introduces a dual-dimensional Recursive Self-Improvement (RSI) framework that enables AI agents to automatically optimize both their tooling (Harness) and deliverables (research papers, algorithms) on the WorkSwarm platform, with compute-affinity scheduling on Ascend NPUs cutting latency and resource usage, validated by SWE-bench pass-rate gains from 61% to 87%.
AI agentsAscend NPUCompute Affinity
0 likes · 15 min read

WorkSwarm's Persistent Session enables AI agents to maintain context, responsibilities, and decisions across hundreds of interaction turns, demonstrated via a 6-hour, 189-turn multi-user Feishu collaboration resolving 8 cross-responsibility conflicts and a 200-turn coding task where the persistent session completed all tasks while the control group failed at turn 156 due to context compression drift.
AI agentsContext DriftContext Management
0 likes · 15 min read

The openJiuwen platform introduces a semantic coordination layer called Agent Hint, together with SAM and SPM managers, to align agent task states with compute resources, achieving a 57% reduction in first‑token latency, a 27.6% drop in end‑to‑end latency, a 33% increase in cache hit rate, and a 25% decrease in storage peak for multi‑agent inference workloads.
Agent HintAscend NPUCompute Affinity
0 likes · 11 min read

The keynote explains how agent architectures have evolved from Prompt, Context, and Harness Engineering to the new Coordination and Symbiosis Engineering paradigms, and how JiuwenSwarm’s AgentOS tackles the enterprise‑level challenges of multi‑agent collaboration, mission‑critical workflows, and large‑scale production deployment.
AI agentsAgentOSSymbiosis Engineering
0 likes · 3 min read

SwarmFlow, the open‑source workflow engine from openJiuwen, separates orchestration from intelligence to make multi‑agent collaborations stable, repeatable, and reusable, addressing leader bottlenecks, process instability, and unreliable execution in complex AI Agent tasks.
AI agentsSwarmFlowWorkflow Orchestration
0 likes · 13 min read

The openJiuwen community introduces Coordination Engineering, a new paradigm that lets multiple AI agents form autonomous, self‑organizing teams through the Agent Team Engine, encapsulated in reusable Team Skills and shared via the Team Skills Hub, with examples ranging from renovation planning to multi‑disciplinary medical consultations.
AI collaborationAgent Team Enginecoordination engineering
0 likes · 15 min read
