Skip to main content
Back to challenges
Challenge

Simulate Dynamic Multifamily Yield Negotiations with AutoGen

Multifamily revenue management systems struggle to balance tenant inquiry conversion speed with dynamic yield optimization during leasing surges. Build an AutoGen multi-agent system to simulate tenant-landlord lease negotiations and optimize occupancy rates within 5% of target yield targets.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Construct an AutoGen multi-agent simulation framework with dynamic pricing feedback loops between tenant agents and property management pricing agents.

Delivery guide

How work is evaluated

Evaluation

Evaluates negotiation completion rate, price convergence, and target yield compliance.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

Price Range Boundary Test

Verifies final rent is within min_acceptable_rent and tenant_max_budget bounds.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

Yield Optimization Alignment

Absolute variance from mathematical optimal yield point. • target: 0.05 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Build conversational multi-agent simulation loops in AutoGen between Tenant and Landlord agents.

  • Integrate dynamic pricing tools into the Landlord agent to optimize lease term lengths and concession packages.

  • Evaluate conversation turn thresholds and market equilibrium price convergence.

Resources and assets

Reference links and supporting material

Dataset notes

Multifamily demand elasticity records with tenant price sensitivity profiles and property manager revenue targets.

Challenge setup

Evaluates negotiation completion rate, price convergence, and target yield compliance.

Challenge input

JSON with unit_asking_rent, min_acceptable_rent, tenant_max_budget, target_lease_months

AutoGen

Assigned framework for multi-agent negotiation dynamics.

Evaluated output

JSON with final_agreed_rent, agreed_lease_months, deal_closed, variance_from_asking

Evaluation checks
  • Verifies final rent is within min_acceptable_rent and tenant_max_budget bounds.
  • Absolute variance from mathematical optimal yield point. • target: 0.05 • range: 0-1
Configured evaluation evidence
  • Benchmark: Agent_Negotiation_Eval
  • Yield Optimization Alignment target: 0.05
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • AutoGen · Required
  • Aim · Optional
  • Sarvam AI · Optional

Evaluation contract

  • Price Range Boundary Test · Weight 1
  • Yield Optimization Alignment · Weight 1

Metrics

  • Yield Optimization Alignment · Target 0.05

Benchmarks

  • Agent_Negotiation_Eval
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with unit_asking_rent, min_acceptable_rent, tenant_max_budget, target_lease_months

    Output: JSON with final_agreed_rent, agreed_lease_months, deal_closed, variance_from_asking

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Simulate Dynamic Multifamily Yield Negotiations with AutoGen