01
Understand the structure of the problem
Two instances with the same job count can need different search methods. Time-window slack, skill scarcity, resource substitutability, geography, prerequisites, and work already in progress all affect feasibility and the value of search.
Start with explicit features and relationships. Add learned representations or change state encodings when downstream gains justify the computing cost.
02
From selecting algorithms to designing search methods
A method specifies how to build an initial solution, prioritize moves, combine neighborhoods, perturb and repair plans, and allocate the budget across stages. LLMs can propose hypotheses and candidate programs for isolated runs and scenario benchmarks.
| Participant | Role | Current scope |
|---|---|---|
| Optimization engine | Run search, score results, and explain constraints | Implemented in vrp-1. Performance varies by instance, budget, and environment. |
| LLMs and agents | Interpret requirements, propose candidates, coordinate tools, and explain results | Method generation and workflow search still need dedicated validation. |
| Rules, specialized models, and short trials | Predict candidate performance, shortlist, and allocate budget | Learned predictions and Jev-style semantic assessment are research topics. |
| Operations teams | Confirm key business rules, trade-offs, and adoption | Business objectives require human approval. |
03
vrp-1 solver benchmark
The first public synthetic benchmark compares vrp-0 and vrp-1 on six shared scenarios. It runs cold construction and continued optimization from identical starting routes separately. Each run uses one solver thread and a 30-second budget, with five random seeds per group.
Curves use observed best-solution events. Total driving hours appear once all five seeds have fully assigned plans with zero hard violations. Shading shows the min–max range. Time includes preprocessing and construction. Each plot has its own vertical scale. Percentages are the median paired changes in driving time against vrp-0.
Charts are drawn from best-solution events and paired statistics in the first vrp-1 benchmark. The results apply to those versions, configurations, scenarios, and budgets. New methods are tested on representative scenarios and regression suites before human approval for promotion.
04
Online decisions and offline engine improvement
Intake routing selects a published workflow. Solver routing selects the strategy, engine version, configuration, and budget. The runtime validates assets, pins immutable versions, and manages scheduling and results. Engines solve within resource limits and send results back for explanation, comparison, adjustment, and approval.
Online results and human feedback feed the scenario and regression sets. Validated offline assets become available to online routing after approval. Versioning, audit, security, authorization, cost, and quotas apply to both loops. Map and travel-matrix services are external dependencies. Compute and storage support the runtime.
05
Capability status and research
| Status | Description |
|---|---|
| Implemented | vrp-1 core, workbench, isolated execution, business constraints, heuristic search, incremental scoring, independent full scoring, explanations, and execution replanning. |
| Validated | Evidence with documented data, baselines, budgets, and scope. Historical cases and demos have their own labels. |
| In development | Platform-level experiments across alternatives and guided infeasibility adjustments are in development. Delivery scope depends on the version. |
| Roadmap and research | Learned problem representations, instance-level performance prediction, dynamic operator combinations, program generation, agent workflow search, and transfer across scenarios. |
Existing components include greedy insertion, warm starts, relocate, swap, Or-opt, perturbation and repair, Late Acceptance, multiple starts, and candidate neighborhoods. Default configurations depend on benchmark results across instances and budgets.
Models propose candidates for deterministic computation, rules, simulations, real cases, and human acceptance to verify. Independent full scoring checks the returned plan. A global optimum requires a separate proof.
06
Working with existing approaches
| Approach | Strengths | Implementation considerations |
|---|---|---|
| Manual planning | Familiar with operations and local exceptions | Trade-offs across operations, scaling, and repeatability |
| In-house development | Fit to internal processes and control over data | Optimization expertise, engineering, and long-term maintenance |
| Off-the-shelf platforms and GIS APIs | Maps, routes, and standard capabilities | Multiple resources, specialist constraints, and domain workflows |
| Specialized optimization software | Mature modeling and optimization | Scenario adaptation, integration, and ongoing delivery |
| Custom implementation services | Tailored to a specific problem | Version reuse, ongoing operations, and expansion |
PsiAI connects business modeling, optimization, and continuous verification. It can work alongside existing tools and infrastructure.
Start with a concrete planning problem.
Contact the PsiAI team ↗