# ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

arXiv: https://arxiv.org/abs/2610.01184 · HTML: https://mlsanity.com/paper/2610.01184/

## 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 22 of its 48 references that are in the map.
- First posted on arXiv 1 Oct 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, 22 of 22)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning](https://mlsanity.com/paper/2402.12185/) (2024)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following](https://mlsanity.com/paper/2403.03129/) (2024)
- [Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems](https://mlsanity.com/paper/2505.15000/) (2025)
- [Can LLMs get help from other LLMs without revealing private information?](https://mlsanity.com/paper/2404.01041/) (2024)
- [Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries](https://mlsanity.com/paper/2506.07555/) (2025)
- [DP-Fusion: Token-Level Differentially Private Inference for Large Language Models](https://mlsanity.com/paper/2507.04531/) (2025)
- [Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning](https://mlsanity.com/paper/2510.16054/) (2025)
- [Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees](https://mlsanity.com/paper/2508.20736/) (2025)
- [Privacy Preserving Visual Question Answering](https://mlsanity.com/paper/2202.07712/) (2022)
- [Safeguarding Privacy in Edge Speech Understanding with Tiny Foundation Models](https://mlsanity.com/paper/2502.01649/) (2025)
- [Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation](https://mlsanity.com/paper/2608.09140/) (2026)
- [Look Twice before You Leap: A Rational Framework for Localized Adversarial Anonymization](https://mlsanity.com/paper/2512.06713/) (2025)
- [Demystifying the Privacy-Utility Trade-off in LLM Interactions](https://mlsanity.com/paper/2609.10992/) (2026)

## Abstract (arXiv)

Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction agent generates and validates the required media from the protected record. The remote solver returns a program whose protected operands are restored locally before execution. On 4,000 held-out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of unprotected remote accuracy, while a model-based audit flags source-content leakage in 7.95% of solver-bound requests. It outperforms all evaluated local baselines, preserving the benefit of remote reasoning while reducing source-content exposure under existing media interfaces.