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
最新资讯
言栖资讯收录 139315 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。
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
BRIDGE: Bridging the Semantic Quantization Gap for Generative Recommendation
arXiv:2611.07425v1 Announce Type: new Abstract: Generative recommendation retrieves items by autoregressively generating Semantic IDs(SIDs), where an RQ-VAE qua…
EnglisharXiv cs.IR
CacheGraft: Enhancing Retrieval-Augmented Generation via Latent-Space Document Enrichment
arXiv:2611.07393v1 Announce Type: new Abstract: Recent work in machine learning has demonstrated that transformer-based language model agents can communicate st…
EnglisharXiv cs.IR
Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens
arXiv:2611.07298v1 Announce Type: new Abstract: Embedding models compress variable-length text into fixed-size vector representations, but this compression can …
EnglisharXiv cs.IR
Requirements Nobody Wrote Down: Emergence in a Public-Sector ML Pipeline
arXiv:2611.07951v1 Announce Type: new Abstract: Governments increasingly use machine learning (ML) to handle data volumes beyond their analytical capacity, yet …
EnglisharXiv cs.SE
A Low Similarity Score Does Not Show Independence after Source-Conditioned Repository Rewriting
arXiv:2611.07887v1 Announce Type: new Abstract: Maintainers sometimes cite a low token-similarity score as evidence that an LLM-assisted rewrite of a copyleft p…
EnglisharXiv cs.SE
Compositional Loop Invariant Inference for Multiphase Programs via Structured Neurosymbolic Reasoning
arXiv:2611.07882v1 Announce Type: new Abstract: Loop invariants are essential for deductive program verification, yet automatically inferring them for {multipha…
EnglisharXiv cs.SE
Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness
arXiv:2611.07876v1 Announce Type: new Abstract: Large language models increasingly judge code, yet without external feedback such judgments are unreliable, and …
EnglisharXiv cs.SE
Adapt the Object to the Subject: Representative Study Material for Empirical Software Engineering
arXiv:2611.07772v1 Announce Type: new Abstract: External validity is a central concern in empirical software engineering, yet the debate has largely focused on …
EnglisharXiv cs.SE
Fast Unsupervised Anomaly Detection Methods on Software Logs - An Empirical Study
arXiv:2611.07760v1 Announce Type: new Abstract: Anomaly detection on software logs ensures system reliability through failure identification, root cause analysi…
EnglisharXiv cs.SE
ReConMem: A Graph-Based Dual Memory System for Repository-Oriented Conversations
arXiv:2611.07759v1 Announce Type: new Abstract: LLM-based code assistants are increasingly used in iterative repository-level development, where effective assis…
EnglisharXiv cs.SE
Uncovering Systematic Blind Spots in Graph Database Testing through Integration and Process-Level Analysis
arXiv:2611.07754v1 Announce Type: new Abstract: Graph databases are becoming foundational infrastructure for connected data, and a growing body of automated tes…
EnglisharXiv cs.SE
Fix One, Miss Another: Leveraging Historical Bug Fixes to Uncover Residual Bugs in Database Systems
arXiv:2611.07739v1 Announce Type: new Abstract: Database management systems (DBMSs) implement SQL constructs through grammar-driven dispatch handlers. Although …
EnglisharXiv cs.SE
What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays
arXiv:2611.07650v1 Announce Type: new Abstract: Third-party application programming interface (API) relays offer access to large language models (LLMs), often a…
EnglisharXiv cs.SE
AiXapply: Fast and Reliable Full-File Code Integration with Specialized Small Models for IDE Workflows
arXiv:2611.07634v1 Announce Type: new Abstract: Large language models increasingly assist developers by proposing small code edits, yet reliably integrating a p…
EnglisharXiv cs.SE
Evolver: Turning Agent Exploration into Evolving Capabilities
arXiv:2611.07595v1 Announce Type: new Abstract: Agent exploration produces valuable procedural knowledge, yet much of this experience remains confined to transi…
EnglisharXiv cs.SE