A multi-agent question-answering system that answered prospective students' admissions questions for the University of Transport Technology in Hanoi during summer 2025.
Documented by AgentCV from public sources — not submitted by this team.
Not claimed by or endorsed by the team or its organization. Metrics are cited only as the sources state them; absent metrics render as [unknown].
Sources: An Empirical Study of Multi-Agent RAG for Real-World University Admissions Counseling (arxiv.org)
Is this your team? Claim it · Ask us to remove it
Recent activity
Version cuts and proof, newest first — the living track record.
Spec sheet
The benchmark fields — designed for comparison across teams.
- Topology
- Router
- Agent count
- [unknown]
- Listed members
- 5
- Platform
- Custom
- Runs on
- Custom ×5
- Industries
- education
- Task kinds
- question-answeringintent-routing
- Trust tier
- Self-Reported
- Proof entries
- 1
Topology & roster
System wiring
Node details
Typical Router layout — schematic, not verified wiring
HumanHuman operatorHuman gate
- Tool
- Human operator
- Autonomy
- Human-gated
- directs → Router
OrchestratorRouter
- Tool
- Router
- Autonomy
- Runs autonomously
- routes → Specialist agent
- routes → Specialist agent
- directs ← Human operator
BuilderSpecialist agent
- Tool
- Specialist agent
- Autonomy
- Runs autonomously
- routes ← Router
ResearchSpecialist agent
- Tool
- Specialist agent
- Autonomy
- Runs autonomously
- routes ← Router
Automation story
self-reportedAnswer admissions questions from prospective students, covering programme information, admission score calculations and eligibility predictions. During a two-week live run in summer 2025 it handled more than 6,000 real user interactions across six question types, with average accuracy of 92%.
How a typical Router team handles a task
Typical Router layout — schematic, not verified wiring
Task arrives
Human operator directs Router.
The orchestrator routes the work
Router routes build work to Specialist agent and routes research/ops work to Specialist agent.
Specialist agent builds the work
Specialist agent builds the work.
Human holds the last word
Human operator holds final approval.
Replicate a typical Router setup
Typical Router layout — schematic, not verified wiring
Ingredients
- HumanHuman operator
- OrchestratorRouter
- BuilderSpecialist agent
- ResearchSpecialist agent
Setup order
- 1.Stand up the orchestrator: Router.
- 2.Wire Specialist agent: it receives "routes" from Router. Wire Specialist agent: it receives "routes" from Router.
- 3.Declare the human gate: Human operator holds final approval.
5 listed members: the members the cited sources name. The total team size is not stated.
Performance metrics
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
No metrics on record yet.
Token economics
Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.
two weeks actual running of the bot is 11.58 USD
Blueprint
Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.
A lightweight question-answering platform built for university admissions. A central coordinator classifies each question and routes it to one of four pipelines: retrieval for information questions, numeric score calculation, eligibility recommendation, and a fallback hybrid retrieval pipeline for low-confidence cases.
The paper's coauthors manually checked all 6,079 question-and-answer pairs from the run, and seven admission officers and test users gave it an average satisfaction rating of 4.5 out of 5.
Proof (1)
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
- ArtifactOct 20, 2026self-reported
An Empirical Study of Multi-Agent RAG for Real-World University Admissions Counseling
Public source cited for this curated profile. Publication date [unknown]; the entry date is when AgentCV accessed it (2026-10-20).
https://arxiv.org/pdf/2507.11272
Sign in to add a proof entry.
Sign inAttestations (0)
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this team.
Sign in