Large Language Models (LLMs) have shown strong capabilities in open-domain question answering (QA), but deploying them in real-world online systems introduces critical challenges. These include: (1) handling both simple and complex queries with appropriate levels of reasoning, (2) minimizing latency without compromising answer quality, and (3) maintaining answer consistency under evolving and noisy retrieval contexts. To address these challenges, we propose Retain-to-Refine (ℜ2ℜ), an adaptive agent-based QA framework designed for practical deployment. ℜ2ℜ integrates a Query Critic Agent (QCA) to assess query difficulty and route it accordingly: simple queries are answered directly using fast, prompt-based LLM calls, while complex queries are handled by a Memory Augmented Agent (MAA). MAA performs iterative reasoning guided by a unique long-short memory mechanism. Long-term memory retains and consolidates stable, core facts to ground the reasoning process, while short-term memory identifies transient information gaps to formulate highly focused subsequent queries. To ensure evidence quality, a Supervised Retrospection module validates and filters retrieved documents at each step. This agent-based design enables ℜ2ℜ to dynamically allocate computation based on question complexity, reducing unnecessary overhead while preserving high-quality answers when multi-step reasoning or external knowledge is required. Extensive evaluations across various settings and datasets demonstrate that the efficiency of R2R across diverse question types. In online settings, ℜ2ℜ delivers substantial gains in both response quality and efficiency, making it well-suited for large-scale industrial deployment in real-time QA services.

Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classification. However, most existing approaches rely heavily on large-scale contrastive learning and offer limited exploration of how the architectural and training paradigms of MLLMs affect embedding quality. While effective for generation, the causal attention and next-token prediction paradigm of MLLMs does not explicitly encourage the formation of globally compact representations, limiting their effectiveness as multimodal embedding backbones. To address this, we propose CoCoA, a Content reconstruction pre-training paradigm based on Collaborative Attention for universal multimodal representation learning. Specifically, we restructure the attention flow and introduce an EOS-based reconstruction task, encouraging the model to reconstruct input from the corresponding (EOS) embeddings. This drives the multimodal model to compress the semantic information of the input into the (EOS) token, laying the foundations for subsequent contrastive learning. Extensive experiments on MMEB-V1 demonstrate that CoCoA built upon Qwen2-VL and Qwen2.5-VL significantly improves embedding quality. Results validate that content reconstruction serves as an effective strategy to maximize the value of existing data, enabling multimodal embedding models to generate compact and informative representations, raising their performance ceiling. Our project is available at https://github.com/Trustworthy-Information-Access/CoCoA.

In commercial web search, aligning content freshness with user intent remains challenging due to the highly varied lifespans of information. Traditional industrial approaches rely on static time-window filtering, resulting in ''one-size-fits-all'' rankings where content may be chronologically recent but semantically expired. To address this limitation, we present a novel Large Language Models (LLMs)-based Query Aware Dynamic Content Expiration Prediction Framework deployed in Baidu search, reformulating timeliness as a dynamic validity inference task. Our framework extracts fine-grained temporal contexts from documents and leverages LLMs to deduce a query-specific ''validity horizon'', a semantic boundary defining when information becomes obsolete based on user intent. Integrated with robust hallucination mitigation strategies to ensure reliability, our approach has been evaluated through offline and online A/B testing on live production traffic. Results demonstrate significant improvements in search freshness and user experience metrics, validating the effectiveness of LLM-driven reasoning for solving semantic expiration at an industrial scale.

Search agents enables large language models (LLMs) to iteratively interleave retrieval and reasoning, yielding strong performance on knowledge-intensive tasks. However, their multi-step autonomy also introduces substantial inefficiencies. In practice, search agents often exhibit overretrieval, where redundant or irrelevant documents are repeatedly fetched, and overthinking, where reasoning steps become excessive or unproductive. Both behaviors significantly inflate retrieval and inference cost, yet remain poorly understood, particularly under model scaling. In this work, we conduct a systematic study of overthinking and overretrieval in search agents from a scaling perspective. We formalize both phenomena at the trajectory level and propose fine-grained evaluation protocols that combine automatic statistics with LLM-based judgments. Through controlled experiments across search agents built on LLMs of varying sizes, we find that increasing model capacity generally alleviates both behaviors, but to markedly different extents. Building on these analysis results, we further propose a lightweight post-hoc reflection framework that converts the proposed evaluation signals into explicit feedback rewards to guide agents' reasoning trajectories. Our findings provide a principled foundation for diagnosing and controlling inefficiencies in search agents.

Search engines are crucial as they provide an efficient and easy way to access vast amounts of information on the Internet for diverse information needs. User queries, even with a specific need, can differ significantly. Prior research has explored the resilience of ranking models against typical query variations like paraphrasing, misspellings, and order changes. Yet, these works overlook how diverse demographics uniquely formulate identical queries. For instance, older individuals tend to construct queries more naturally and in varied order compared to other groups. This demographic diversity necessitates enhancing the adaptability of ranking models to diverse query formulations. To this end, in this article, we propose a framework that integrates a novel rewriting pipeline that rewrites queries from various demographic perspectives and a novel framework to enhance ranking robustness. To be specific, we use Chain of Thought (CoT) technology to utilize Large Language Models (LLMs) as agents to emulate various demographic profiles, then use them for efficient query rewriting, and we innovate a Robust Multi-gate Mixture-of-Experts (R-MMoE) architecture coupled with a hybrid loss function, collectively strengthening the ranking models’ robustness. Our extensive experiments on both public and industrial datasets assesses the efficacy of our query rewriting approach and the enhanced accuracy and robustness of the ranking model. The findings highlight the sophistication and effectiveness of our proposed model. We release our code implementation publicly ( https://github.com/Applied-Machine-Learning-Lab/ROBR ).

Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods often depend on fine-tuning with task-specific labels, limiting their effectiveness when labeled data is scarce. Our research tackles this by advancing graph model generalization in zero-shot learning environments. Inspired by the success of large language models (LLMs), we aim to create a graph-oriented LLM capable of exceptional generalization across various datasets and tasks without relying on downstream graph data. We introduce the GraphGPT framework, which integrates LLMs with graph structural knowledge through graph instruction tuning. This framework includes a text-graph grounding component to link textual and graph structures and a dual-stage instruction tuning approach with a lightweight graph-text alignment projector. These innovations allow LLMs to comprehend complex graph structures and enhance adaptability across diverse datasets and tasks. Our framework demonstrates superior generalization in both supervised and zero-shot graph learning tasks, surpassing existing benchmarks. The open-sourced model implementation of our GraphGPT is available at https://github.com/HKUDS/GraphGPT.

Text-video retrieval is a challenging task that aims to identify relevant videos given textual queries. Compared to conventional textual retrieval, the main obstacle for text-video retrieval is the semantic gap between the textual nature of queries and the visual richness of video content. Previous works primarily focus on aligning the query and the video by finely aggregating word-frame matching signals. Inspired by the human cognitive process of modularly judging the relevance between text and video, the judgment needs high-order matching signal due to the consecutive and complex nature of video contents. In this paper, we propose chunk-level text-video matching, where the query chunks are extracted to describe a specific retrieval unit, and the video chunks are segmented into distinct clips from videos. We formulate the chunk-level matching as n-ary correlations modeling between words of the query and frames of the video and introduce a multi-modal hypergraph for n-ary correlation modeling. By representing textual units and video frames as nodes and using hyperedges to depict their relationships, a multi-modal hypergraph is constructed. In this way, the query and the video can be aligned in a high-order semantic space. In addition, to enhance the model's generalization ability, the extracted features are fed into a variational inference component for computation, obtaining the variational representation under the Gaussian distribution. The incorporation of hypergraphs and variational inference allows our model to capture complex, n-ary interactions among textual and visual contents. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on the text-video retrieval task.

The problem of data sparsity has long been a challenge in recommendation systems, and previous studies have attempted to address this issue by incorporating side information. However, this approach often introduces side effects such as noise, availability issues, and low data quality, which in turn hinder the accurate modeling of user preferences and adversely impact recommendation performance. In light of the recent advancements in large language models (LLMs), which possess extensive knowledge bases and strong reasoning capabilities, we propose a novel framework called LLMRec that enhances recommender systems by employing three simple yet effective LLM-based graph augmentation strategies. Our approach leverages the rich content available within online platforms (e.g., Netflix, MovieLens) to augment the interaction graph in three ways: (i) reinforcing user-item interaction egde, (ii) enhancing the understanding of item node attributes, and (iii) conducting user node profiling, intuitively from the natural language perspective. By employing these strategies, we address the challenges posed by sparse implicit feedback and low-quality side information in recommenders. Besides, to ensure the quality of the augmentation, we develop a denoised data robustification mechanism that includes techniques of noisy implicit feedback pruning and MAE-based feature enhancement that help refine the augmented data and improve its reliability. Furthermore, we provide theoretical analysis to support the effectiveness of LLMRec and clarify the benefits of our method in facilitating model optimization. Experimental results on benchmark datasets demonstrate the superiority of our LLM-based augmentation approach over state-of-the-art techniques. To ensure reproducibility, we have made our code and augmented data publicly available at: https://github.com/HKUDS/LLMRec.git.

Recommender systems have seen significant advancements with the influence of deep learning and graph neural networks, particularly in capturing complex user-item relationships. However, these graph-based recommenders heavily depend on ID-based data, potentially disregarding valuable textual information associated with users and items, resulting in less informative learned representations. Moreover, the utilization of implicit feedback data introduces potential noise and bias, posing challenges for the effectiveness of user preference learning. While the integration of large language models (LLMs) into traditional ID-based recommenders has gained attention, challenges such as scalability issues, limitations in text-only reliance, and prompt input constraints need to be addressed for effective implementation in practical recommender systems. To address these challenges, we propose a model-agnostic framework RLMRec that aims to enhance existing recommenders with LLM-empowered representation learning. It proposes a recommendation paradigm that integrates representation learning with LLMs to capture intricate semantic aspects of user behaviors and preferences. RLMRec incorporates auxiliary textual signals, employs LLMs for user/item profiling, and aligns the semantic space of LLMs with collaborative relational signals through cross-view alignment. This work further demonstrates the theoretical foundation of incorporating textual signals through mutual information maximization, which improves the quality of representations. Our evaluation integrates RLMRec with state-of-the-art recommender models, while also analyzing its efficiency and robustness to noise data. Implementation codes are available at https://github.com/HKUDS/RLMRec.

Community Question Answering (CQA) sites such as Yahoo! Answers and Baidu Knows have emerged as rich knowledge resources for information seekers. However, answers posted to CQA sites often vary a lot in their qualities. User votes from the community may partially reflect the overall quality of the answer, but they are often missing. Hence, automatic selection of "good'' answers becomes a practical research problem that will help us manage the quality of accumulated knowledge. Without loss of generality, a good answer should deliver not only relevant but also trustworthy information that can help resolve the information needs of the posted question, but the latter has received less investigation in the past. In this paper, we propose a novel matching-verification framework for automatic answer selection. The matching component assesses the relevance of a candidate answer to a given question as conventional QA methods. The major enhancement is the verification component, which aims to leverage the wisdom of crowds, e.g., some big information repository, for trustworthiness measurement. Given a question, we take the top retrieved results from the information repository as the supporting evidences to distill the consensus representation. A major challenge is that there is no guarantee that one can always obtain reliable consensus from the wisdom of crowds for a question due to the noisy nature and the limitation of the existing search technology.Therefore, we decompose the trustworthiness measurement into two parts, i.e., a verification score which measures the consistency between a candidate answer and the consensus representation, and a confidence score which measures the reliability of the consensus itself. Empirical studies on three real-world CQA data collections, i.e. YahooQA, QuoraQA and AmazonQA, show that our approach can significantly outperform the state-of-the-art methods on the answer selection task.

Machine reading comprehension (MRC) has become a core component in a variety of natural language processing (NLP) applications such as question answering and dialogue systems. It becomes a practical challenge that an MRC model needs to learn in non-stationary environments, in which the underlying data distribution changes over time. A typical scenario is the domain drift, i.e. different domains of data come one after another, where the MRC model is required to adapt to the new domain while maintaining previously learned ability. To tackle such a challenge, in this work, we introduce the Continual Domain Adaptation (CDA) task for MRC. So far as we know, this is the first study on the continual learning perspective of MRC. We build two benchmark datasets for the CDA task, by re-organizing existing MRC collections into different domains with respect to context type and question type, respectively. We then analyze and observe the catastrophic forgetting (CF) phenomenon of MRC under the CDA setting. To tackle the CDA task, we propose several BERT-based continual learning MRC models using either regularization-based methodology or dynamic-architecture paradigm. We analyze the performance of different continual learning MRC models under the CDA task and show that the proposed dynamic-architecture based model achieves the best performance.

Reading comprehension (RC) aims to locate a text span from a context passage to answer the given question. Despite the effectiveness of modern neural RC models, most existing work relies on maximum likelihood estimation (MLE) and ignores the structure of the output space. That is during training, one treats all the text spans do not match the ground truth as equally poor, leading to overconfident predictions on ground truth labels and reduced generalization ability in test. One way to bridge the gap between training and test is to take into account the task reward of alternative outputs using the reinforcement learning (RL) algorithms, which is often deficient in optimization as compared with MLE. In this paper, we propose a new learning criterion for the RC task which combines the merits of both MLE and RL-based methods. Specifically, we show that we are able to derive the distribution of the outputs, i.e., label distribution, using their corresponding task rewards based on the decomposition property of the RC problem. We then optimize the RC model by directly learning towards the auxiliary label distribution, instead of the ground truth label, using the MLE framework. In this way, we can make use of the structure of the output space for better generalization (as RL) via efficient optimization (as MLE). We name our approach as Label Distribution augmented MLE (LD-MLE), which is a general learning criterion that could be adopted by almost all the existing RC models. Experiments on three representative benchmark datasets demonstrate that RC models learned with the LD-MLE criterion can achieve consistently improved results over those based on the traditional MLE and RL-based criteria.

Web question answering (QA) has become an dispensable component in modern search systems, which can significantly improve users' search experience by providing a direct answer to users' information need. This could be achieved by applying machine reading comprehension (MRC) models over the retrieved passages to extract answers with respect to the search query. With the development of deep learning techniques, state-of-the-art MRC performances have been achieved by recent deep methods. However, existing studies on MRC seldom address the predictive uncertainty issue, i.e., how likely the prediction of an MRC model is wrong, leading to uncontrollable risks in real-world Web QA applications. In this work, we first conduct an in-depth investigation over the risk of Web QA. We then introduce a novel risk control framework, which consists of a qualify model for uncertainty estimation using the probe idea, and a decision model for selectively output. For evaluation, we introduce risk-related metrics, rather than the traditional EM and F1 in MRC, for the evaluation of risk-aware Web QA. The empirical results over both the real-world Web QA dataset and the academic MRC benchmark collection demonstrate the effectiveness of our approach.