AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation
arXiv:2603.03761v2 Announce Type: replace-cross Abstract: LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a…
EnglisharXiv cs.IR
最新资讯
言栖资讯收录 139030 篇 AI、开发与建站文章（English），按发布时间排序，支持搜索与按语言筛选。
Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation
arXiv:2610.37973v2 Announce Type: replace Abstract: LLM-based generative recommendation reads long, text-rich interaction histories but generates only short sem…
EnglisharXiv cs.IR
Multimodal Graph RAG for Long-range Visually Rich Document Understanding
arXiv:2606.28780v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are widely applied to visual document understanding. However, compr…
EnglisharXiv cs.IR
HyperSU: Corpus-Driven Semantic-Unit Hypergraph for Retrieval-Augmented Generation
arXiv:2606.28351v3 Announce Type: replace Abstract: Recent Hypergraph-based retrieval-augmented generation (HyperRAG) methods use hyper edges to connect multipl…
EnglisharXiv cs.IR
HGCRS: Hypergraph-Enhanced Generative Conversational Recommender System
arXiv:2605.21987v2 Announce Type: replace Abstract: Recent conversational recommender systems have begun to unify recommendation and response generation within …
EnglisharXiv cs.IR
EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
arXiv:2605.12887v3 Announce Type: replace Abstract: Web-enabled LLM agents are changing how online information influences search outcomes. Existing Generative E…
EnglisharXiv cs.IR
OneRanker: Unified Generation and Ranking with One Model in Industrial Advertising Recommendation
arXiv:2603.02999v4 Announce Type: replace Abstract: The end-to-end generative paradigm is revolutionizing advertising recommendation systems, driving a shift fr…
EnglisharXiv cs.IR
FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL
arXiv:2512.12084v3 Announce Type: replace Abstract: Existing Text-to-SQL benchmarks primarily focus on single-table queries or limited joins in general-purpose …
EnglisharXiv cs.IR
Decision Models as Retrieval Gates Against Injection and Pollution
arXiv:2611.08325v1 Announce Type: cross Abstract: Retrieved web text can carry instructions aimed at the language model, or synthetic pages written to mislead. …
EnglisharXiv cs.IR
ArcadeDB in Python: An In-Process Multi-Model Database
arXiv:2611.07971v1 Announce Type: cross Abstract: Some Python workflows need transactional reads and writes over documents, traversals over a graph, and similar…
EnglisharXiv cs.IR
Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency
arXiv:2611.07899v1 Announce Type: cross Abstract: Conversational agents can retrieve information directly or delegate retrieval to a subagent. This design choic…
EnglisharXiv cs.IR
CORE: Coarse-to-Fine Search with Context Management for Deep Research
arXiv:2611.07859v1 Announce Type: cross Abstract: Deep research agents answer complex questions through repeated search. They rely on a harness that runs their …
EnglisharXiv cs.IR
MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports
arXiv:2611.07486v1 Announce Type: cross Abstract: Mapping behavioral intelligence in malware analysis reports to ATT&CK techniques supports threat analysis and …
EnglisharXiv cs.IR
MapHub: Daily Relevance Heatmaps of New arXiv Preprints for a Research Community
arXiv:2611.07174v1 Announce Type: cross Abstract: MapHub, the MIDAS arXiv Preprint Hub, assesses each day's new arXiv submissions for every participant in a res…
EnglisharXiv cs.IR
Domain-specific information retrieval
arXiv:2611.08228v1 Announce Type: new Abstract: Information Retrieval (IR) is much more than ad hoc web search: a large portion of the information seeking activ…
EnglisharXiv cs.IR
Probabilistic Relevance Decisions for Semantic Retrieval
arXiv:2611.08014v1 Announce Type: new Abstract: Dense similarity supplies reusable corpus representations, while probabilistic relevance decisions offer query-d…
EnglisharXiv cs.IR
MEMOIR: A Training-Free Memory Lifecycle for Long-Horizon LLM Agents
arXiv:2611.07631v1 Announce Type: new Abstract: Long-horizon LLM agents require memory systems that preserve useful information across sessions and retrieve it …
EnglisharXiv cs.IR
Beyond Independent Predictions: Learning the Browsing Journey for Sequence-Level Re-ranking
arXiv:2611.07591v1 Announce Type: new Abstract: Re-ranking aims to present users with an ordered list that maximizes sequence-level utility. Industrial deployme…
EnglisharXiv cs.IR
What Gets Hacked in a Collaborative Reward for LLM Recommenders: The Part That Does Not Depend on the User
arXiv:2611.07588v1 Announce Type: new Abstract: Collaborative-filtering (CF) scores provide graded, personalized rewards for training large language model (LLM)…
EnglisharXiv cs.IR
OptST: Optimizing Semantic Tokenization for LLM-Enhanced Recommendation
arXiv:2611.07523v1 Announce Type: new Abstract: Semantic information can enrich the identifiers and structured fields used by recommender systems. Semantic toke…
EnglisharXiv cs.IR