Multimodal long documents are core carriers of professional knowledge, where critical evidence is sparsely distributed across paragraphs and modalities. This easily causes key information omission and cross-modal hallucinations in summarization by multimodal LLMs. These issues stem from attention drift in long-range dependency modeling and gaps in inter-modal alignment. To address this, we introduce MMLDSum-Bench, a high-quality benchmark for multimodal long-document summarization, covering multiple domains, context-length scales, and visual-textual modality distributions. We further propose MMLDSum-LLM, a reproducible two-stage training framework that combines supervised fine-tuning with visual-alignment weighted loss and keyword-aware weighted loss, followed by GRPO with a multi-objective reward (keyword coverage, image-text alignment, ROUGE, and length control). Extensive experiments on MMLDSum-Bench, comparing against leading closed-source and open-source multimodal models under a unified evaluation protocol — including LLM-as-a-judge scoring, atomic-claim precision/recall, image-text alignment (ITA), and ROUGE — demonstrate that our approach significantly improves key-information coverage and cross-modal consistency.

Reward-aware variants of Direct Preference Optimization (DPO), such as ODPO and MODPO, implicitly assume linear marginal utility over the preference signal: identical signal gaps induce identical gradient updates regardless of whether the pair lies in a low- or high-quality region. We propose FreeMU, a lightweight plug-and-play training module that introduces non-linear marginal utility through a pair-aware divided-difference weight applied directly to the preference margin. The same weight formula integrates with three representative DPO variants—ODPO, MODPO, and β-DPO—with each instantiation differing only in the reward source and its normalisation. We first instantiate FreeMU on the two explicit-score variants (Likert labels for ODPO and reward-model outputs for MODPO) and then, for variants without externally annotated scores, on β-DPO using the implicit Bradley–Terry reward induced by the policy and reference models. Across summarization, multi-objective safety alignment, and dialogue, FreeMU consistently improves over its host in LLM-based win rates and task-specific metrics with near-zero training overhead; a controlled ablation confirms that the convex curvature direction is the operative ingredient—reversing the sign to a concave utility removes the gain.

Mobile Phone Agents (MPAs) have emerged as a promising research direction due to their broad applicability across diverse scenarios. While Multimodal Large Language Models (MLLMs) serve as the foundation for MPAs, their effectiveness in handling multiple mobile phone tasks simultaneously remains limited. Although multitask supervised fine-tuning (SFT) is widely adopted for multitask learning, existing approaches struggle to determine optimal training data compositions for peak performance. To address this challenge, we propose DaMo (Data Mixture Optimizer) – a novel solution employing a trainable network that predicts optimal data mixtures by forecasting downstream task performance for any given dataset ratio. To support comprehensive evaluation, we introduce PhoneAgentBench, the first specialized benchmark to evaluate MLLMs on multimodal mobile phone tasks, comprising 1,235 QA pairs spanning diverse real-world industrial mobile application scenarios. Demonstrating strong predictive capability (R²=0.81) in small-scale pilot experiments, DaMo efficiently extrapolates optimal data mixing configurations. Our results show DaMo achieves 3.06% average score improvement on PhoneAgentBench and open-source benchmarks, including BFCL-v3, MME-Reasoning, MME-Perception, and OCRBench, compared to alternative methods. Through predicting optimal data mixture only on open-source benchmarks, DaMo outperforms other approaches by 6.70% in terms of average score. Moreover, DaMo improves the metrics by 12.74% than other methods when used solely for MLLM optimization on the BFCL-v3 task. Notably, DaMo maintains robust scalability, preserving its effectiveness when applied to other model architectures.

The effectiveness of large language models (LLMs) in conversational AI is hindered by their reliance on single-turn supervised fine-tuning (SFT) data, which limits contextual coherence in multi-turn dialogues. Existing methods for generating multi-turn dialogue data struggle to ensure both diversity and quality in instructions. To address this, we propose Review-Instruct, a novel framework that synthesizes multi-turn conversations through an iterative “Ask-Respond-Review” process involving three agent roles: a Candidate, multiple Reviewers, and a Chairman. The framework iteratively refines instructions by incorporating Reviewer feedback, enhancing dialogue diversity and difficulty. We construct a multi-turn dataset using the Alpaca dataset and fine-tune the LLaMA2-13B model. Evaluations on MT-Bench, MMLU-Pro, and Auto-Arena demonstrate significant improvements, achieving absolute gains of 2.9% on MMLU-Pro and 2% on MT-Bench compared to prior state-of-the-art models based on LLaMA2-13B. Ablation studies confirm the critical role of the Review stage and the use of multiple Reviewers in boosting instruction diversity and difficulty. Our work highlights the potential of review-driven, multi-agent frameworks for generating high-quality conversational data at scale.

Large Language Models (LLMs) can teach small language models (SLMs) to solve complex reasoning tasks (e.g., mathematical question answering) by Chain-of-thought Distillation (CoTD). Specifically, CoTD fine-tunes SLMs by utilizing rationales generated from LLMs such as ChatGPT. However, CoTD has certain limitations that make it unsuitable for knowledge-intensive multi-hop question answering: 1) SLMs have a very limited capacity in memorizing required knowledge compared to LLMs. 2) SLMs do not possess the same powerful integrated abilities in question understanding and knowledge reasoning as LLMs. To address the above limitations, we introduce Decompose-and-Response Distillation (D&R Distillation), which distills two student models, namely Decomposer and Responser separately. The two models solve a knowledge-intensive multi-hop question through an interactive process of asking and answering subquestions. Our method offers two advantages: 1) SLMs have the capability to access external knowledge to address subquestions, which provides more comprehensive knowledge for multi-hop questions. 2) By employing simpler subquestions instead of complex CoT reasoning, SLMs effectively mitigate task complexity and decrease data prerequisites. Experimental results on three knowledge-intensive multi-hop question answering datasets demonstrate that D&R Distillation can surpass previous CoTD methods, even with much less training data.