LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation

Multi-armed bandit algorithms, especially Thompson sampling, are widely used in online recommendation. Despite their ability to adapt from online feedback, these methods often suffer from cold-start l...

arxiv.org

Search, Inspect, Fetch: Exploiting Boolean Retrieval for Deep-Research Agents

Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web sources expose through titles, headings, sections...

arxiv.org

Coverage Matters: MarginMerge for Compressing Multi-Vector Visual Document Retrievers

Multi-vector visual document retrievers such as ColPali and ColQwen achieve strong retrieval by storing fine-grained patch embeddings, but this produces large indexes and costly late-interaction scori...

arxiv.org

Position Bias Undermines Preference Consistency in Listwise LLM-Based Reranking

Large language models (LLMs) have emerged as promising listwise rerankers for recommender systems, but their reliability under equivalent candidate permutations remains unclear. Since recommendation c...

arxiv.org

UniGD: A Unified Generative-Discriminative Framework for Industrial Retrieval

Generative retrieval (GR) is a promising paradigm for industrial search advertising, yet its deployment is constrained by strict relevance and latency requirements. Existing systems cascade GR with an...

arxiv.org

RAG-Stack: Co-Optimizing RAG Serving Performance and Quality

Retrieval-augmented generation (RAG), which augments large language model (LLM) generation with information retrieved from databases, has become a widely used approach for knowledge-intensive applicat...

arxiv.org

Training Documents Reranker with Search Rubrics for Deep Research Agent

Retrieval systems help deep research agents generate high-quality answers by providing relevant documents. However, existing retrievers typically select documents through relevance matching, while ind...

arxiv.org

SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation

As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate items. Existing met...

arxiv.org

ATLAS: Learning to Recommend Across Unseen Domains

Recommender systems remain domain-bound: a model trained on one interaction environment typically requires retraining or target-domain adaptation before it can operate on a new catalogue. A recommende...

arxiv.org

EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents

Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit cannot distinguish the contributions of individual...

arxiv.org

PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent

Existing search-augmented LLM agents are trained using Reinforcement Learning to boost its reasoning capabilities. However, these approaches primarily rely on outcome-level rewards, which provide litt...

arxiv.org

Before Reasoning Fails: Pre-Evidence Procedural Failures in Agentic RAG

Agentic retrieval-augmented generation (RAG) systems can fail before evidence-conditioned reasoning is tested: an agent may retrieve candidate snippets but finalize without inspecting them. We study t...

arxiv.org

Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answering

The effective use of search engines by large language models (LLMs) remains a significant challenge, particularly in complex, multi-hop question-answering (MHQA) tasks. These tasks require the model t...

arxiv.org

HindSearch: Trajectory-Level Hindsight Critique for Search-Augmented Reinforcement Learning

Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed. We introduce HindSearch, a hindsight...

arxiv.org

TEngineDB-V: An OLAP-Native Vector Search System for Large-$k$ Workloads at Tencent

Vector search systems are essential infrastructure for modern data-driven applications. Large-$k$ analytical vector search, which retrieves $k=10^3$--$10^5$ results for analytics (e.g., aggregation, f...

arxiv.org

Cross-Domain Hybrid OPD for Generalizable Search Agents

Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning, and iterative retrieval over dynamic informati...

arxiv.org

SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems

SIRIN (Semantic Inconsistency Recognition and Inspection Nexus) is a unified toolkit and interactive web UI for detecting contextual hallucinations (fluent, plausible responses unsupported by the prov...

arxiv.org

H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing represen...

arxiv.org

Hierarchical BM25: Lexical Search at Billion-Document Scale

A flat BM25 index over one billion documents occupies about 400 GB. Holding it in memory requires DRAM proportional to corpus size. Serving it from disk takes 4-12 seconds per query. Exact top-k lexic...

arxiv.org

CeQe: Grounding Lexical Retrieval in Semantic Evidence

Lexical retrieval (BM25) captures exact keyword matches and weights terms by corpus-wide significance, but it is blind to the semantic vocabulary gap: when a relevant document phrases an answer differ...

arxiv.org

Hierarchical Residual Policy Optimization for Generative Recommendations

Generative recommenders select items by autoregressively decoding semantic identifiers (SIDs), whose token positions induce a coarse-to-fine hierarchy over the item space. In practice, SID decoders ar...

arxiv.org

Exponential Reward Weighting for Fine-Tuning Generative Recommenders under Sparse and Noisy Feedback

In recommendation systems, users interact with only a small fraction of a vast item catalog, producing feedback that is both sparse and noisy. This challenges post-training generative recommenders: re...

arxiv.org

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

Modern reranking recipes---billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers---have outpaced the training infrastructure available to most acad...

arxiv.org

GRACE: Generative Recommender Acceleration Engine for Real-Time Ads Retrieval

Productionizing generative recommenders for high-volume, real-time ads retrieval creates two serving challenges: eligibility, ensuring that each generated ad is eligible for the request under the adve...

arxiv.org

Auditing Semantic Gains in Sequential Recommendation: A Lightweight Recovery Test

Recent semantic and generative-retrieval recommenders report substantial improvements over ID-only sequential baselines, but it remains unclear whether these gains arise from language-model reasoning,...

arxiv.org

Collaborative Memory Augmentation for Generative Recommendation

Generative Recommendation (GR) has exhibited great potential by modeling item transitions as a sequence-to-sequence task. Despite the success of GR, existing frameworks primarily focus on modeling ind...

arxiv.org

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection

Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internalized Generation), a holistic paradigm spanning bo...

arxiv.org

Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents

Deep search agents answer difficult information-seeking questions by iteratively issuing search queries to gather supporting evidence, but it remains unclear whether and how greater search effort lead...

arxiv.org

A Self-Triggered Agentic Push Recommendation System

Push notification is a critical recommendation scenario on large-scale platforms, allowing the system to proactively reach users outside the application to improve long-term re-engagement. However, de...

arxiv.org

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents

Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence. This creates a stopping problem: after the necessary evidence has appeared,...

arxiv.org