arXiv AI October 2, 2026 By Bingchen Pei, Lichong Chen, Bingxi Zhao, Ziang Wu, Sirui Wang, Min Zhang, Yanhao Chen, Qingxu Liu, Qiang Gao, Chang-Tien Lu, Bo Gao

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

Read the original on arXiv AI →

ReCast is a plug‑in framework that protects private inputs for fixed‑interface multimodal reasoning by locally converting them into a shared textual evidence‑query record, rewriting entities and topics with a distilled model, and mapping numerical values through an invertible, role‑aware map. A reconstruction agent then generates the required media from this protected record, allowing a remote solver to return a program whose operands are restored locally before execution. On 4,000 held‑out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of the unprotected remote accuracy, and flags source‑content leakage in 7.95% of solver‑bound requests, outperforming all evaluated local baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Oct 1

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

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 satis...

agents multimodal

arXiv AI

6d ago

Walking the Embedding Space: Datastore Extraction from Multimodal RAG

arXiv:2610. 01871v1 Announce Type: cross Abstract: Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a reliable and cost-effective technique of grounding the generative capabilities of Multimodal Large Language Models (MLLMs) into relevant, up-to-date, external knowledge.

By Maria Carmen Jica, Ali Satvaty, Suzan Verberne, Fatih Turkmen

llms rag multimodal

arXiv AI

Jun 24

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

arXiv:2606. 24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts.

By Yuanhe Zhao, Tianyu Zhang, Huafei Xing, Derek F. Wong, Jianbin Li, Tao Fang

llms rag agents safety

Hugging Face Trending Papers

Jul 30

LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger

Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy. This aggregate signal cannot tell whether a correct answer was reached through grounded evidence, language priors, or accidental error cancellation.

agents nlp multimodal benchmarks safety

arXiv Machine Learning

Jul 31

LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger

arXiv:2607. 28374v1 Announce Type: new Abstract: Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy.

By Enjun Du, Hange Zhou, Chenxu Du, Siyi Liu, Zirong Chen, Ziyu Zheng, Yongqi Zhang

agents nlp multimodal benchmarks safety

arXiv Machine Learning

Aug 13

LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection

arXiv:2608. 11691v1 Announce Type: new Abstract: Reinforcement-learning (RL) post-training equips multimodal large reasoning models (MLRMs) with exploratory chains of thought (CoT), substantially improving visual reasoning.

By Xinhao Zhong, Yuxia Qiao, Junhao Li, Hao Fang, Yi Sun, Bin Chen

rag reinforcement-learning multimodal safety

One email a morning, machine-written

Related stories

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

Walking the Embedding Space: Datastore Extraction from Multimodal RAG

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger

LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger

LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection