Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

M2Note: Continual Evolution of Vision Language Models via Mistake Notebook Learning

About

Vision Language Models (VLMs) have demonstrated remarkable capabilities in multimodal reasoning tasks, yet they still suffer from recurring failures, such as skipping key visual checks, misapplying domain rules, and hallucinating unsupported concepts. Most existing solutions rely on supervised fine-tuning (SFT) and reinforcement learning (RL), which are expensive to iterate and can be brittle under distribution shift. To this end, we propose Multimodal Mistake Notebook Learning (M2Note), a training-free continual evolution framework that externalizes learning into an editable memory. M2Note transforms failed trajectories into compact subject-guidance notes: the subject summarizes the underlying domain and concept, while the guidance provides actionable verification steps that can be reused in future inference. At test time, M2Note retrieves relevant notes via multimodal retrieval-augmented generation (RAG) and appends them to the model context, steering reasoning away from previously observed pitfalls. To stabilize continual evolution, we adopt batch-level post-verification with rollback, which commits notebook edits only if they improve performance on the same batch, reducing noisy updates and preventing regressions. M2Note supports both self-evolving, where the same VLM acts as solver and supervisor, and cross-model evolving, where a stronger supervisor guides a weaker solver, enabling capability transfer without weight updates. Experiments on six multimodal reasoning benchmarks show consistent improvements across domains and backbones, while achieving strong cost and sample efficiency and remaining complementary to Chain-of-Thought (CoT) prompting.

Haiwen Li, Jing Tang, Rui Chen, Lei Sun, Xiangxiang Chu• 2026

Related benchmarks

TaskDatasetResultRank
Real-world QARealworldQA
Accuracy81.8
75
General VQAMMStar
Accuracy69.4
51
STEM & PuzzleMMMU (val)
Accuracy79.7
26
STEM PuzzleMathVista
Accuracy83.9
15
Document OCRChartQA
Accuracy0.917
15
Document OCRAI2D
Accuracy86.5
13
Multimodal ReasoningMultimodal Reasoning Aggregate 6 benchmarks
Average Score80.8
11
Showing 7 of 7 rows

Other info

Follow for update