Summarize this content to 100 words:
[Submitted on 24 Jan 2026 (v1), last revised 4 Mar 2026 (this version, v3)]
View a PDF of the paper titled Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models, by Yicheng Bao and 5 other authors
View PDF
HTML (experimental)
Abstract:Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, which are prohibitively expensive to scale and impose a ceiling on model robustness. We introduce \textbf{AOT-SFT}, a large-scale adversarial dataset for bootstrapping MLLM robustness. Building on this, we propose \textbf{AOT (Adversarial Opponent Training)}, a self-play framework that forges MLLM robustness by creating its own training data. Our method orchestrates a co-evolution between an image-editing Attacker and a Defender MLLM, where the Attacker generates a diverse and dynamic curriculum of image manipulations, forcing the Defender to adapt and improve. Extensive experiments demonstrate that AOT enhances the Defender’s perceptual robustness and reduces hallucinations, establishing a scalable paradigm for training more reliable MLLMs.
Submission history From: Yicheng Bao [view email] [v1]
Sat, 24 Jan 2026 03:47:29 UTC (14,820 KB)
[v2]
Fri, 27 Feb 2026 05:20:42 UTC (14,820 KB)
[v3]
Wed, 4 Mar 2026 11:04:46 UTC (14,820 KB)
