Domain-specific finetuning is essential for dense retrievers, yet not all data pairs contribute equally to the learning process. We introduce OPERA1 , a data pruning framework that exploits this heter...

Contextual information in recommender systems is shifting from static, predefined variables toward latent representations inferred from behavior. Large language models support this shift by rendering ...

Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces a failure mode we c...

Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experimental loop. Over long horizons, execution accura...

Generative recommendation (GR) has emerged as an alternative to embedding-based retrieval, building on the success of generative models in language and vision. We are exploring GR on Facebook Forum, a...

Generative retrieval with semantic identifiers (SIDs) makes successive decisions over a document hierarchy. Relevant documents for the same query may share coarse prefixes and diverge at finer depths,...

Generative retrieval has emerged as a general retrieval paradigm, representing items with discrete Semantic IDs (SIDs) and retrieving them through autoregressive identifier generation. When SIDs are c...

Generative retrieval reformulates recommendation as the generation of discrete item tokens. However, scaling this paradigm to real-world recommender systems reveals two critical bottlenecks: 1) Repres...

Large language models (LLMs) have shown promise for recommendation reranking, but their use introduces an important tradeoff between recommendation quality and serving efficiency. We investigate wheth...

We present LongCat-DeepResearch, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded reports. The workflow separat...

A critical prerequisite of generative recommendation is designing semantic identifiers (SIDs) that are both scalable to large item sets and efficiently learnable. Existing SID learning methods fundame...

Large-scale recommender systems, particularly short-form video platforms, are often bottlenecked by massive popularity feedback loops. In such environments, as models recommend popular items, they gen...

Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by learning to interleave search and reasoning. Ho...

Industrial recommendation systems rely on multi-stage cascades whose retrieval, ranking, and serving components are difficult to replace jointly. We present GRP, a generative recommendation framework ...

Industrial recommendation ranking models typically scale along two modeling axes: feature interaction over heterogeneous user, item, context, and cross features, and sequence modeling over long, infor...

Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirem...

Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without providing the facts needed to answer. Even when ins...

Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can bridge vocabulary gaps with the target corpus. Any...

Scientific queries are often brief, while relevant papers use specialized vocabulary. Generated query expansion can bridge this mismatch, but earlier work suggests that its value shrinks as the underl...

Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training. In this paper, we ask whether LLMs can instead be prompted to produce...

Extracting conditional text embeddings from large language models (LLMs) is a promising paradigm, as it requires neither additional data nor fine-tuning. Existing methods incorporate conditions into p...

On-policy self-distillation densifies agent training without external teachers: a policy conditioned on privileged hindsight provides step-level guidance for its own unprivileged rollouts. For search ...

A central limitation of current data-free self-evolution methods for training search agents is their reliance on difficulty-based proposer rewards. These methods reward a proposer for generating quest...

Foundation model recommender systems require user context that can be consumed by large language models, reasoned over, and refined through natural-language interaction. Traditional behavioral embeddi...

Document rerankers determine what evidence reaches the downstream model in RAG and deep research, yet mainstream rerankers select by relevance matching, and individually relevant documents rarely cons...

Offline evaluation is the dominant experimental paradigm in recommender systems research, enabling reproducible and cost-effective comparisons on historical interaction data. Yet, while considerable a...

Transformers have redefined sequential recommendation by effectively modeling dynamic user behaviors and long-range dependencies. However, they remain inherently inefficient: standard architectures op...

Dense retrieval powers retrieval-augmented generation, semantic search, and question answering, yet the theoretical basis for choosing between shared and dual query-document projections remains unclea...

Visual document retrieval requires expressive representations to match queries with evidence distributed across text, tables, and page layouts. Multi-vector representations capture fine-grained inform...

Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measurements: the same observed behavior can arise from d...

RAG and retrieval-based agent memory both inject retrieved content into LLM prompts, as document chunks and recalled memory records, respectively. The same content can recur across requests at differe...

Multimodal large language models can expose task-relevant evidence through generation, but producing useful evidence does not by itself determine how it enters a retrieval embedding. We study whether ...

Generative recommenders retrieve items by generating identifiers, but a valid identifier can remain outside the beam after catalog expansion. This raises two connected questions: which failures can id...

Semantic ID (SID) based generative recommendation represents each item as a sequence of discrete tokens, and recommends by generating the SID of the item a user would like to interact with. Both domin...

Leveraging the strong generative capabilities and stable training dynamics of diffusion models, diffusion-based recommender systems (RSs) have recently emerged as a novel recommendation paradigm, attr...

Modern recommender systems advance not only by scaling data and parameters, but also by encoding task-specific inductive biases through architecture, including sparse feature interactions for click-th...

Multi-vector retrievers built on vision-language models lead visual document retrieval (VDR), but they run a multi-billion-parameter query encoder on every search. Distilling this encoder into a small...

AutoResearch improves systems through iterative experimentation: agents propose candidate modifications, evaluate them, and use the results to guide subsequent exploration. Applying this paradigm to i...

Rendering document text as images allows vision-language models to encode documents as visual tokens, which can reduce input sequence length compared with text input. This reduction in input length is...

Generative retrieval (GR) enables end-to-end retrieval by generating document semantic identifiers (SIDs). However, retrieval-only fine-tuning can over-specialize pretrained language models to SID pre...

Rerankers decide which documents users and LLMs see, yet their standard metric, nDCG, relies on human relevance labels that are costly, sparse, noisy, and discretely graded. As rerankers approach each...

Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but also on user preferences, product constraints, and...

Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g., "recommend Italian indie artists I haven't hear...

Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation along with design choices made for text, includi...

Modern industrial recommender systems must optimize across competing objectives, balancing semantic relevance with business metrics such as engagement and revenue. While bi-encoders dominate large-sca...

Large-scale recommendation models pose distinct, under-explored profiling challenges. Most recommendation model architectures are structurally heterogeneous, intermixing memory-bandwidth-bound operati...

Sequential recommendation optimizes which items to rank, while each displayed slate also shapes subsequent feedback and user state. We study how a trained ranker can support decisions about these futu...

Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools to resolve user intent. However, ...

Passage reranking plays a crucial role in information retrieval by refining the ordering of candidate passages to better reflect relevance. Existing listwise LLM rerankers with Chain-of-Thought (CoT) ...

Conversational agents, generative recommenders, and personalized advertising all rest on one capability: understanding each user from raw behavior. Prevailing industrial practice is task-specific: for...