Existing tool-augmented large language models (LLMs) encounter significant challenges when processing complex queries. Current frameworks such as ReAct are prone to local optimization traps due to their reliance on incremental decision-making processes. To address these limitations, we propose a novel Planner-centric Plan-Execute paradigm that fundamentally resolves local optimization bottlenecks through architectural innovation. Central to our approach is a novel Planner model that performs global Directed Acyclic Graph (DAG) planning for complex queries, enabling optimized execution beyond conventional tool coordination. We also introduce ComplexTool-Plan, a large-scale benchmark dataset featuring complex queries that demand sophisticated multi-tool composition and coordination capabilities. Additionally, we develop a two-stage training methodology that integrates Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), systematically enhancing the Planner's tool selection accuracy and global planning awareness through structured DAG-based planning. When integrated with a capable executor, our framework achieves state-of-the-art performance on the StableToolBench benchmark for complex user queries, demonstrating superior end-to-end execution capabilities and robust handling of intricate multi-tool workflows.

Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging.Existing methods often face difficulties with contextual grounding, cross-modal interpretation ambiguity, and single-pass reasoning fragility.To address these, we propose Retrieval-Augmented Multi-modal Multiagent Stance Detection (MM-StanceDet), a novel multi-agent framework integrating Retrieval Augmentation for contextual grounding, specialized Multimodal Analysis agents for nuanced interpretation, a Reasoning-Enhanced Debate stage for exploring perspectives, and Self-Reflection for robust adjudication.Extensive experiments on five datasets demonstrate MM-StanceDet significantly outperforms state-of-the-art baselines, validating the efficacy of its multi-agent architecture and structured reasoning stages in addressing complex multimodal stance challenges.

Large Language Models (LLMs) have demonstrated remarkable creative writing capabilities, yet their substantial computational demands hinder widespread use.Enhancing Small Language Models (SLMs) offers a promising alternative, but current methods like Supervised Fine-Tuning (SFT) struggle with novelty, and Reinforcement Learning from Human Feedback (RLHF) is costly.This paper explores two distinct AI-driven reward strategies within a Reinforcement Learning from AI Feedback (RLAIF) framework to ignite the creative writing of a 7B-parameter SLM, specifically for generating Chinese greetings.The first strategy employs a RM trained on high-quality preference data curated by a novel multi-agent rejection sampling framework designed for creative tasks.The second, more novel strategy utilizes a principle-guided LLM-as-a-Judge, whose reward function is optimized via an adversarial training scheme with a reflection mechanism, to directly provide reward signals.Comprehensive experiments reveal that while both approaches significantly enhance creative output over baselines, the principle-guided LLM-as-a-Judge demonstrably yields superior generation quality.Furthermore, it offers notable advantages in training efficiency and reduced dependency on human-annotated data, presenting a more scalable and effective path towards creative SLMs.Our automated evaluation methods also exhibit strong alignment with human judgments.Our code and data are publicly available at Github.

Lately, the academic community has been showing growing interest in multi-domain fake news detection, and in particular, incorporating multimodal information into this field has emerged as a highly promising research direction. However, existing methods often struggle with: (1) Insufficient intrinsic domain adaptation during representation Learning; (2) Amplified negative transfer from entangled domain style and content representations; and (3) Neglecting domain-varying modality uncertainty. To address these issues, we propose Domain-Aware Prompt Tuning (DAPT), an innovative framework for multimodal multi-domain fake news detection. DAPT leverages Multimodal Prompt Tuning for parameter-efficient domain adaptation of pretrain models. An Adaptive Domain Debias Module disentangles domain features from veracity signals guided by content to mitigate negative transfer. Furthermore, inspired by the Variational Information Bottleneck, an Uncertainty-Aware Multimodal Fusion mechanism adaptively aggregates modalities based on domain-specific reliability. Extensive experiments demonstrate that DAPT significantly outperforms state-of-the-art baselines on benchmark datasets.

In click-through rate prediction, click-through rate prediction is used to model users' interests. However, most of the existing CTR prediction methods are mainly based on the ID modality. As a result, they are unable to comprehensively model users' multi-modal preferences. Therefore, it is necessary to introduce multi-modal CTR prediction. Although it seems appealing to directly apply the existing multi-modal fusion methods to click-through rate prediction models, these methods (1) fail to effectively disentangle commonalities and specificities across different modalities; (2) fail to consider the synergistic effects between modalities and model the complex interactions between modalities.

The sequential recommendation system utilizes historical user interactions to predict preferences. Effectively integrating diverse user behavior patterns with rich multimodal information of items to enhance the accuracy of sequential recommendations is an emerging and challenging research direction. This paper focuses on the problem of multi-modal multi-behavior sequential recommendation, aiming to address the following challenges: (1) the lack of effective characterization of modal preferences across different behaviors, as user attention to different item modalities varies depending on the behavior; (2) the difficulty of effectively mitigating implicit noise in user behavior, such as unintended actions like accidental clicks; (3) the inability to handle modality noise in multi-modal representations, which further impacts the accurate modeling of user preferences. To tackle these issues, we propose a novel Multi-Modal Multi-Behavior Sequential Recommendation model (M3BSR). This model first removes noise in multi-modal representations using a Conditional Diffusion Modality Denoising Layer. Subsequently, it utilizes deep behavioral information to guide the denoising of shallow behavioral data, thereby alleviating the impact of noise in implicit feedback through Conditional Diffusion Behavior Denoising. Finally, by introducing a Multi-Expert Interest Extraction Layer, M3BSR explicitly models the common and specific interests across behaviors and modalities to enhance recommendation performance. Experimental results indicate that M3BSR significantly outperforms existing state-of-the-art methods on benchmark datasets.