2026年10月30日 · 星期五

TRENDING

热门排行

所有条目按 LLM 评分排序。点击卡片看详情，点击标题直达原文。

必读 · 85+ 2 条

重要 · 70–84 15 条

值得关注 · 50–69 19 条

arXiv cs.IR arXiv 检索/推荐论文 60

Lossless Compression of Proximity Graph Indexes for Efficient Approximate Nearest Neighbors Search

Graph-based Approximate Nearest Neighbor (ANN) indexes, such as HNSW, are the backbone of modern vector search. However, their massive memory footprint creates a severe infrastructure bottleneck. While vector quantization is widely adopted to reduce the memory required to store data vectors, the graph's edge structure increasingly dominates total memory usage. Compressing these adjacency lists for

T1 AWS ML 国际公司动态 56

Building an Agentic AI Platform on Amazon Bedrock AgentCore

Stand up a governed, multi-account Agentic AI Platform on Amazon Bedrock AgentCore. This post walks through the architecture and an open-source reference blueprint: the operating model, control plane, per-Workstream cells, separate inference and tool gateways, and a CI/CD evaluation pipeline that gates each agent before production.

arXiv cs.IR arXiv 检索/推荐论文 54

AutoRSE: Evaluating LLM Agents as Recommendation Engineers for Self-Evolving Recommender Systems

Recommender Systems Engineer Agents (RSE-Agents), which use LLM-based agents to autonomously improve recommendation algorithms, are emerging as a promising paradigm. However, their capabilities and limitations remain poorly understood due to the lack of a unified, standardized evaluation framework and systematic trajectory-level analysis. To address this gap, we introduce AutoRSE, an evaluation fr

GitHub Trending GitHub 热门趋势 53

CopilotKit/OpenBot

Open-source AI coworkers that each get a computer of their own: a browser, files...

arXiv cs.IR arXiv 检索/推荐论文 52

When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG

Retrieval-augmented generation (RAG) can benefit from more sophisticated retrieval, but extra retrieval may be unnecessary for many questions and gains in evidence retrieval may not translate into faithful or correct answers. We study a cost-aware, two-action retrieval policy that chooses between a dense-retrieval-plus-reranking baseline and a hybrid lexical--dense retriever. Rather than classifyi

T1 AWS ML 国际公司动态 51

Distributed training with Ray Train DLCs and EFA on EKS

The Ray Train Deep Learning Container ships the full CUDA-through-EFA stack, so you build no image. This post walks through a reproducible sample that fine-tunes Qwen2.5-1.5B with PyTorch FSDP across eight GPUs on two EFA-enabled g6.12xlarge instances on Amazon EKS, using the container exactly as published.

一般 · <50 12 条

T1 NVIDIA 国际公司动态 48

Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents

Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and checking that the scene behaves as intended. Developers are combining frontier AI models with NVIDIA Omniverse libraries to help carry out that work — building applications for exploring scenarios, investigating failures and improving designs. Developers direct AI agents through […]

GitHub Trending GitHub 热门趋势 47

obra/superpowers

An agentic skills framework & software development methodology that works.

T1 AWS ML 国际公司动态 47

How MoEngage turned over 400 APIs into agent tools with AgentCore Gateway

MoEngage turned roughly 400 private REST APIs across 7 AWS Regions into permission-scoped agent tools with Amazon Bedrock AgentCore Gateway. No per-service MCP servers, no public endpoints, and no 400-tool context bloat. See how OpenAPI specs, Cedar policies, and managed Amazon VPC Lattice egress made it work.

GitHub Trending GitHub 热门趋势 45

pbakaus/impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, revie...

GitHub Trending GitHub 热门趋势 43

nightly-labs/openbot

A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, ...

arXiv cs.IR arXiv 检索/推荐论文 42

REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation

Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendation (GR) offers a promising paradigm by autoregressively generating discrete semantic IDs (SIDs) of items. However, randomly initialized SID token embeddings and GR models trained from scratch do not directly inherit the semantic relation

另有 1 家报道
GitHub Trending GitHub 热门趋势 41

thedotmack/claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your ag...

arXiv cs.IR arXiv 检索/推荐论文 36

LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation

We present LCM-Promo, an LLM-based uplift model for promotion allocation. LCM-Promo is a task-specific Large Commerce Model (LCM): a finetuned LLM trained on transactional commerce data to predict user intent and promotion response. It learns monotonic promotion-response curves from production logs by interpreting single-token outputs as conversion-threshold probabilities, while conditioning on se