SPIN Unprocessed August 17, 2026 ai_technology research
Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision
View original on arxiv.orgOverview
arXiv:2608.13854v1 Announce Type: new Abstract: Code translation must preserve executable behavior across many programming languages, yet neural code translation has largely focused on a few popular languages such as C++, Java, and Python. This leaves a niche, many-to-many setting where parallel supervision is sparse, producing plausible but non-executable translations. We address this setting with preference-based reinforcement learning driven by execution-based supervision. Our pipeline firstl
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from arXiv Computation and Language
View all →- Batch-wise Adaptive Pruning: Periodic Neuron Activation-Aware Weight Pruning for Language Reasoning Model
- Repair, Not Improvement: Decomposing Constrained Decoding in Tool-Call Abstention
- Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion
- ASSERT: A Measurement Pipeline for GenAI Audits
- When Lexical Change Misleads: Rethinking Dynamic Topic Model Evaluation with Traditional and LLM-Based Metrics
- Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO