Repository-scale refactoring requires coding agents to propagate a single change across many interdependent files without altering pro- gram behavior, yet to our knowledge no existing harness isolates the design choices that determine agent success on this task. We present RefactorPlatform, an open-source evaluation harness that holds the environment fixed and varies each design axis explicitly: model backbone (via OpenRouter and GitHub Copilot CLI), execution regime (baseline, retrieval-augmented, and multi-agent), and prompt specificity. Each run executes in an isolated workspace with live terminal streaming, per-task logging of tokens, diffs, and transcripts, AST-based verification, and exportable telemetry for audit and reproduction. Demonstrating the platform on 100 multi-file RefactorBench tasks across four model families, we illustrate the analyses it supports: AST-aware chunking outperforms naive token-window chunking by 25-30 percentage points (pp) across prompt modes, whereas naive retrieval falls below the retrieval-free baseline; a lean retrieval-augmented single agent (86%) beats the sub-agent configuration we evaluated (66%) on matched tasks with no task passing under delegation that fails under retrieval; and retrieval’s accuracy gains absorb its token overhead, leaving cost per successful refactoring unchanged. RefactorPlatform is open-sourced to make refactoring-agent evaluation reproducible and auditable.

Legal documents are often long and unstructured, making them challenging and time-consuming to apprehend. An automatic system that can identify relevant entities and labels within legal documents, would significantly reduce the legal research time. We developed a system to streamline legal case analysis from planning courts by extracting key information from XML files using Named Entity Recognition (NER) and multi-label classification models to convert them into structured form. This research contributes three novel datasets for the Planning Court cases: a NER dataset, a multi-label dataset fully annotated by humans, and newly re-annotated multi-label datasets partially annotated using LLMs. We experimented with various general-purpose and legal domain-specific models with different maximum sequence lengths. It was noted that incorporating paragraph position information improved the performance of models for the multi-label classification task. Our research highlighted the importance of domain-specific models, with LegalRoBERTa and LexLM demonstrating the best performance.