Reinforced Collaboration in Multi-Agent Flow Networks — AI framework

Zheng Wang, Yuang Liu, Yangkai Ding/Reinforced Collaboration in Multi-Agent Flow NetworksUnknown

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation, arising from suboptimal workflow design or inaccurate agent outputs, which can propagate through the agent collaboration process and degrade final results. To address the challenges, we present MANGO (Multi-Agent Network Gradient Optimization), a data-driven framework that organizes and refines agent collaboration via a flow network constructed from past successful workflows. MANGO integrates reinforcement learning and textual gradients to jointly optimize workflow paths and agent behaviors, while a skipping mechanism prevents redundant updates to well-optimized agents for improving efficiency. Extensive experiments on seven benchmarks show that MANGO achieves up to 12.8% performance improvement over state-of-the-art baselines, enhances efficiency by 47.4%, and generalizes effectively to unseen domains. Our code and datasets are publicly available at https://github.com/openJiuwen-ai/agent-store/tree/main/community/mango.

framework

Stars0

Forks0

HF Downloads—30d

Last commit—

Refreshed4mo ago

Project healthUnknownNo activity data.

Production readinessResearch / EarlyBest for exploration and prototyping.

Risk notesUnknown licenseVerify license before production use.

AgentHub Score

55 / 100

Composite score from 6 signals. How we score →

Active project

55Score

Growth

40C

Activity

30C

Documentation

70C+

Maturity

45C

Community

42C

Production

58C

GitHub stars · 70 days observed0 not enough history

snapshots

Repository activity · 70 days observedReal snapshots from pushed_at

inactivepushed

2026-07-262026-10-05

Practical assessment

Should you use it?

✓ Best for

Multi-agent orchestration
Production agentic workflows
Stateful long-running tasks

◎ Strengths

Stable API
Active release cadence
Strong GitHub community

✕ Not ideal for

Simple single-step automation
Teams without Python/ML expertise

⚠ Watch-outs

Breaking changes between minor versions
Ecosystem lock-in if tightly coupled

Technical details

What's inside

Language—

License—

Sourcearxiv

Open source✗ No

Commercial use—

Docs—

Demo—

PaperarXiv ↗

AgentHub Score

Score 55/100

Below average

Alternatives

OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings

0 · framework

CHAL: Council of Hierarchical Agentic Language

0 · framework

Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents

0 · framework

Structuring agentic AI for HPC code modernization

0 · framework

55 Compare all →

Recent activity

Latest commit ——

Indexed by AgentHub crawler4mo ago

Monitor for new releasesongoing