# Stage-Supervised Latent Reasoning for Single-Shot JavaScript Deobfuscation

arXiv: https://arxiv.org/abs/2609.27058 · HTML: https://mlsanity.com/paper/2609.27058/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 2 of 2)

- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [JsDeObsBench: Measuring and Benchmarking LLMs for JavaScript Deobfuscation](https://mlsanity.com/paper/2506.20170/) (2025)

## Abstract (arXiv)

JavaScript obfuscation is widely used to protect code, but it also makes program analysis and security review substantially harder. Existing LLM-based deobfuscation methods usually treat the task as one-step translation, ignoring the staged structure of practical deobfuscation pipelines. This WIP paper proposes a stage-aware latent reasoning framework that converts intermediate outputs from a deterministic deobfuscation tool into supervision for Coconut-based training. The model learns from multi-stage rewrites during training but generates the final cleaned program in a single shot at inference time. Preliminary results on JsDeObsBench show that the Coconut-based model improves syntactic validity to 50%, compared with 15% for direct fine-tuning and 25% for a zero-shot baseline, and reaches 80% semantic correctness among valid outputs, indicating better semantic faithfulness than either comparison model in deobfuscation.