PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation

2026-07-02

AI Summary

Existing code-driven generation of structured artifacts—such as charts and 3D scenes—is prone to errors due to the absence of validation feedback from toolchains like compilers and renderers. This work proposes a dual-agent pair programming framework: a Driver agent generates code, while a Navigator agent critiques it based on execution outcomes, diagnostic messages, and rendered visual comparisons. When persistent errors occur, the agents dynamically swap roles, establishing a closed-loop iterative refinement process. This approach represents the first systematic integration of toolchain feedback into multimodal structured generation, substantially improving output executability. Evaluated across 17 benchmarks, the method consistently outperforms baselines—for instance, increasing Blender scene executability from 0.20 to 0.78 and boosting TikZ compilation rates by 10–30 percentage points—at an inference cost approximately seven times that of a single model.

Abstract

Code is the medium through which large language models generate structured artifacts: charts, scientific figures, vector graphics, CAD models, 3D scenes, and hardware designs are all produced by writing programs. In this regime single pass inference is brittle, because the compiler, renderer, or simulator that decides whether the artifact exists is invisible to the model. We present PairCoder, which grounds review in the toolchain and realizes it as two agent pair programming: a Driver agent writes the program, a Navigator agent reviews it against verification evidence (diagnostics, execution results, and renderings of the current artifact beside the target), and the two switch roles when errors persist. Across 17 public benchmarks and seven models from three vendors, PairCoder improves essentially every benchmark whose artifact is verifiable, on full official metric suites rather than execution alone (for example, Blender scene executability 0.20 to 0.78; TikZ compile rate up 10 to 30 points on every model), at 2.9 to 9.2 times single model cost (about 7 times overall). The improvements concentrate where the toolchain provides an informative oracle and the baseline leaves headroom, and the method ties or mildly regresses where the oracle is weak; we frame pair programming as a reliable recipe for verified code driven generation.

Problem

• code-driven generation
• structured artifacts
• verification
• multimodal generation
• pair programming

Innovation

• pair programming
• verified code generation
• multimodal artifact generation
• dual-agent collaboration
• toolchain grounding