Foundation-model agents now use reusable skills for tool use, long-horizon planning, and adaptation across related tasks. The term, however, is used loosely. It may describe a prompt package, an executable workflow, a learned routine, or an artifact distributed through a repository. That looseness makes it hard to compare methods, measure progress, or discuss security and governance with precision.We study agent skills as reusable and adaptive units of competence between model capability and situated task execution. The survey separates skills from nearby constructs such as prompts, tools, memory, and policies, then organizes the literature around representation, lifecycle and orchestration, evaluation, security and governance, and application domains. Across these areas, skill quality is only one part of the story. Useful skills also depend on abstraction choices, retrieval and composition mechanisms, ecosystem structure, and infrastructure security. We treat agent skills as a research object in their own right and identify open problems in automatic induction, cross-environment transfer, longitudinal evaluation, and trustworthy sharing in open agent ecosystems. A public paper list is available at https://github.com/JinhaoShen/awesome-agent-skill-papers.

Foundation-model agents increasingly rely on reusable skills to support tool use, long-horizon planning, and cross-task adaptation. Yet the term remains ambiguous in the literature, where it may refer to prompt packages, executable workflows, learned routines, or repository artifacts. This ambiguity makes it difficult to compare methods, evaluate progress, and reason clearly about security and governance.We study agent skills as reusable and adaptive units of competence that sit between model capability and situated task execution. The survey first separates skills from nearby constructs such as prompts, tools, memory, and policies. It then organizes the literature around representation, lifecycle and orchestration, evaluation, security and governance, and application domains. The evidence suggests that skill quality alone is not enough: useful skills also depend on abstraction choices, retrieval and composition mechanisms, ecosystem structure, and infrastructure security. We therefore treat agent skills as a research object in their own right and identify open problems in automatic induction, cross-environment transfer, longitudinal evaluation, and trustworthy sharing in open agent ecosystems.

Text-guided molecular design is a key capability for AI-driven drug discovery, yet it remains challenging to map sequential natural-language instructions with non-linear molecular structures under strict chemical constraints. Most existing approaches, including RAG, CoT prompting, and fine-tuning or RL, emphasize a small set of ad-hoc reasoning perspectives implemented in a largely one-shot generation pipeline. In contrast, real-world drug discovery relies on dynamic, multi-perspective critique and iterative refinement to reconcile semantic intent with structural feasibility. Motivated by this, we propose Mol-Debate, a generation paradigm that enables such dynamic reasoning through an iterative generate-debate-refine loop. We further characterize key challenges in this paradigm and address them through perspective-oriented orchestration, including developer-debater conflict, global-local structural reasoning, and static-dynamic integration. Experiments demonstrate that Mol-Debate achieves state-of-the-art performance against strong general and chemical baselines, reaching 59.82

Molecular science represents an important frontier for LLM-based agents. Unlike general agents that mainly operate over natural language, code, or web environments, molecular LLM agents must perceive, reason about, and act upon chemical objects across symbolic strings, molecular graphs, 3D conformations, spectra, simulations, and wet-lab measurements. Their capabilities depend on chemically faithful molecular perception, an LLM-centered agent framework, domain-specific tool grounding, and computational or experimental feedback, in addition to planning and tool use. This work develops a conceptual framework for molecular LLM agents from two complementary perspectives. First, we introduce an architectural view of molecular-agent design, covering molecular representation and perception, the agent framework, domain-specific toolboxes, and learning and optimization. Second, we propose a scientific autonomy ladder inspired by staged autonomy in engineering systems, categorizing agents into four levels: L1 assistive or fixed workflows, L2 adaptive computational agents, L3 feedback-aware physical experiment agents, and L4 scientific-agenda agents. Together, these two perspectives establish a comprehensive framework for comparing existing molecular LLM agents, identifying missing capabilities and deployment risks, and guiding the design, evaluation, and deployment of future agents in molecular discovery workflows.

Recent advancements in diffusion models have significantly impacted content creation, leading to the emergence of Personalized Content Synthesis (PCS). By utilizing a small set of user-provided examples featuring the same subject, PCS aims to tailor this subject to specific user-defined prompts. Over the past two years, more than 150 methods have been introduced in this area. However, existing surveys primarily focus on text-to-image generation, with few providing up-to-date summaries on PCS. This paper provides a comprehensive survey of PCS, introducing the general frameworks of PCS research, which can be categorized into test-time fine-tuning (TTF) and pre-trained adaptation (PTA) approaches. We analyze the strengths, limitations, and key techniques of these methodologies. Additionally, we explore specialized tasks within the field, such as object, face, and style personalization, while highlighting their unique challenges and innovations. Despite the promising progress, we also discuss ongoing challenges, including overfitting and the trade-off between subject fidelity and text alignment. Through this detailed overview and analysis, we propose future directions to further the development of PCS.

Accurate human localization is crucial for various applications, especially in the Metaverse era. Existing high precision solutions rely on expensive, tag-dependent hardware, while vision-based methods offer a cheaper, tag-free alternative. However, current vision solutions based on stereo vision face limitations due to rigid perspective transformation principles and error propagation in multi-stage SVD solvers. These solutions also require multiple high-resolution cameras with strict setup constraints.To address these limitations, we propose a probabilistic approach that considers all points on the human body as observations generated by a distribution centered around the body's geometric center. This enables us to improve sampling significantly, increasing the number of samples for each point of interest from hundreds to billions. By modeling the relation between the means of the distributions of world coordinates and pixel coordinates, leveraging the Central Limit Theorem, we ensure normality and facilitate the learning process. Experimental results demonstrate human localization accuracy of 96% within a 0.3m range and nearly 100% accuracy within a 0.5m range, achieved at a low cost of only 10 USD using two web cameras with a resolution of 640×480 pixels.

The accurate categorization of compounds within the anatomical therapeutic chemical (ATC) system is fundamental for drug development and fundamental research. Although this area has garnered significant research focus for over a decade, the majority of prior studies have concentrated solely on the Level 1 labels defined by the World Health Organization (WHO), neglecting the labels of the remaining four levels. This narrow focus fails to address the true nature of the task as a multilevel, multi-label classification challenge. Moreover, existing benchmarks like Chen-2012 and ATC-SMILES have become outdated, lacking the incorporation of new drugs or updated properties of existing ones that have emerged in recent years and have been integrated into the WHO ATC system. To tackle these shortcomings, we present a comprehensive approach in this paper. Firstly, we systematically cleanse and enhance the drug dataset, expanding it to encompass all five levels through a rigorous cross-resource validation process involving KEGG, PubChem, ChEMBL, ChemSpider, and ChemicalBook. This effort culminates in the creation of a novel benchmark termed ATC-GRAPH. Secondly, we extend the classification task to encompass Level 2 and introduce graph-based learning techniques to provide more accurate representations of drug molecular structures. This approach not only facilitates the modeling of Polymers, Macromolecules, and Multi-Component drugs more precisely but also enhances the overall fidelity of the classification process. The efficacy of our proposed framework is validated through extensive experiments, establishing a new state-of-the-art methodology. To facilitate the replication of this study, we have made the benchmark dataset, source code, and web server openly accessible.

Current molecular understanding approaches predominantly focus on the descriptive aspect of human perception, providing broad, topic-level insights. However, the referential aspect – linking molecular concepts to specific structural components – remains largely unexplored. To address this gap, we propose a molecular grounding benchmark designed to evaluate a model's referential abilities. We align molecular grounding with established conventions in NLP, cheminformatics, and molecular science, showcasing the potential of NLP techniques to advance molecular understanding within the AI for Science movement. Furthermore, we constructed the largest molecular understanding benchmark to date, comprising 117k QA pairs, and developed a multi-agent grounding prototype as proof of concept. This system outperforms existing models, including GPT-4o, and its grounding outputs have been integrated to enhance traditional tasks such as molecular captioning and ATC (Anatomical, Therapeutic, Chemical) classification.

Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a phenomenon we term Hallucination on Hallucination. To address this, we propose Debate-Augmented RAG (DRAG), a training-free framework that integrates Multi-Agent Debate (MAD) mechanisms into both retrieval and generation stages. In retrieval, DRAG employs structured debates among proponents, opponents, and judges to refine retrieval quality and ensure factual reliability. In generation, DRAG introduces asymmetric information roles and adversarial debates, enhancing reasoning robustness and mitigating factual inconsistencies. Evaluations across multiple tasks demonstrate that DRAG improves retrieval reliability, reduces RAG-induced hallucinations, and significantly enhances overall factual accuracy. Our code is available at https://github.com/Huenao/Debate-Augmented-RAG.

Accurate human localization is crucial for various applications, especially in the Metaverse era. Existing high precision solutions rely on expensive, tag-dependent hardware, while vision-based methods offer a cheaper, tag-free alternative. However, current vision solutions based on stereo vision face limitations due to rigid perspective transformation principles and error propagation in multi-stage SVD solvers. These solutions also require multiple high-resolution cameras with strict setup constraints. To address these limitations, we propose a probabilistic approach that considers all points on the human body as observations generated by a distribution centered around the body's geometric center. This enables us to improve sampling significantly, increasing the number of samples for each point of interest from hundreds to billions. By modeling the relation between the means of the distributions of world coordinates and pixel coordinates, leveraging the Central Limit Theorem, we ensure normality and facilitate the learning process. Experimental results demonstrate human localization accuracy of 95 100 two web cameras with a resolution of 640x480 pixels.

In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA-NeXT-Video in generating natural language descriptions for video content. We investigate the impact of fine-tuning VLMs on VTT datasets to enhance description accuracy, contextual relevance, and linguistic consistency. Our analysis reveals that fine-tuning substantially improves the model's ability to produce more detailed and domain-aligned text, bridging the gap between generic VLM tasks and the specialized needs of VTT. Experimental results demonstrate that our fine-tuned model outperforms baseline VLMs across various evaluation metrics, underscoring the importance of domain-specific tuning for complex VTT tasks.

This paper presents a pilot study aimed at introducing multi-agent debate into multimodal reasoning. The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images. These challenges stem from the inductive (bottom-up) nature of existing debating schemes. To address the issue, we propose a deductive (top-down) debating approach called Blueprint Debate on Graphs (BDoG). In BDoG, debates are confined to a blueprint graph to prevent opinion trivialization through world-level summarization. Moreover, by storing evidence in branches within the graph, BDoG mitigates distractions caused by frequent but irrelevant concepts. Extensive experiments validate that BDoG is able to achieve state-of-the-art results in ScienceQA and MMBench with significant improvements over previous methods. The source code can be accessed at https://github.com/thecharm/BDoG.

This paper presents a pilot study that explores the application of active learning, traditionally studied in the context of discriminative models, to generative models. We specifically focus on image synthesis personalization tasks. The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept. We introduce the concept of anchor directions to transform the querying process into a semi-open problem. We propose a direction-based uncertainty sampling strategy to enable generative active learning and tackle the exploitation-exploration dilemma. Extensive experiments are conducted to validate the effectiveness of our approach, demonstrating that an open-source model can achieve superior performance compared to closed-source models developed by large companies, such as Google's StyleDrop. The source code is available at https://github.com/zhangxulu1996/GAL4Personalization.

In this paper, we explore the use of large language models (LLMs) to enhance video moment retrieval (VMR) by integrating general knowledge and pseudo-events as priors. We address the limitations of LLMs in generating continuous outputs, such as salience scores and inter-frame embeddings, which are critical for capturing inter-frame relations. To address these limitations, we propose using LLM encoders, which refine inter-concept relations in multimodal embeddings effectively, even without textual training. Our feasibility study shows that this capability extends to other embeddings like BLIP and T5 when they exhibit similar patterns to CLIP embeddings. We present a general framework for integrating LLM encoders into existing VMR architectures, specifically within the fusion module. The LLM encoder's ability to refine concept relation can help the model to achieve a balanced understanding of the foreground concepts (e.g., persons, faces) and background concepts (e.g., street, mountains) rather focusing only on the visually dominant foreground concepts. Additionally, we utilize pseudo-events, identified via event detection, to guide accurate moment prediction within event boundaries, reducing distractions from adjacent moments. Our plug-in approach for semantic refinement and pseudo-event regulation demonstrates state-of-the-art VMR performance through experimental validation. The source code can be accessed at https://github.com/fletcherjiang/LLMEPET.

In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring features through higher-dimensional vectors. To facilitate network optimization, we construct a transformation from scalar to vector using independent angles based on 3D vector rotations. Finally, we develop a PointVector model that follows the structure of PointNeXt. Our experimental results demonstrate that PointVector achieves state-of-the-art performance $\textbf{72.3\% mIOU}$ on the S3DIS Area 5 and $\textbf{78.4\% mIOU}$ on the S3DIS (6-fold cross-validation) with only $\textbf{58\%}$ model parameters of PointNeXt. We hope our work will help the exploration of concise and effective feature representations. The code will be released soon.

The irregularity and disorder of point clouds bring many challenges to point cloud analysis. PointMLP suggests that geometric information is not the only critical point in point cloud analysis. It achieves promising results based on a simple multi-layer perception (MLP) structure with a geometric affine module. However, these MLP-like structures aggregate features only with fixed weights, while differences in the semantic information of different point features are ignored. Therefore, we propose a novel Point-Vector Representation of the point feature to improve feature aggregation by using inductive bias. The direction of the introduced vector representation can dynamically modulate the aggregation of two point features according to the semantic information. Based on this, we design a novel Point2Vector MLP architecture. Experiments show that it achieves state-of-the-art performance on the classification task of the ScanObjectNN dataset, with an 1% increase compared with the previous best method. It also achieves a compective performance on the ShapeNetPart dataset. We hope our method can help people better understand the role of semantic information in point cloud analysis and lead to exploring more and better feature representations or other ways.