Scaling Large-Scale Agent Networks: A Review of Topology, Memory, and Updates

This review examines why some large‑scale multi‑agent systems remain stable while others falter, introducing a three‑dimensional taxonomy—topology, memory scope, and update behavior—to explain scalability limits and highlighting world‑model inconsistency as a deeper bottleneck than communication protocols.

Multi-Agent SystemsScalabilitydynamic updates

0 likes · 9 min read

Scaling Large-Scale Agent Networks: A Review of Topology, Memory, and Updates

AI Frontier Lectures

Jan 27, 2026 · Artificial Intelligence

A Unified Framework for Neural Network Reprogrammability: From Model Reprogramming to Prompt Tuning

This article surveys recent advances in neural network reprogrammability, presenting a unified framework that categorizes model reprogramming, prompt tuning, prompt instruction, and in‑context learning, highlights the shift from parameter‑centric to reprogrammability‑centric adaptation, and provides efficiency analyses, taxonomy, and practical case studies.

Model AdaptationNeural Network ReprogrammabilityPrompt Tuning

0 likes · 16 min read

A Unified Framework for Neural Network Reprogrammability: From Model Reprogramming to Prompt Tuning

Airbnb Technology Team

Nov 3, 2022 · Artificial Intelligence

T-LEAF: A Taxonomy Learning and Evaluation Framework for Airbnb Community Support Classification System

The T‑LEAF framework introduces quantitative metrics for coverage, usefulness, and consistency to iteratively develop Airbnb’s unified Contact‑Reason taxonomy, enabling faster feedback loops, reducing “Other” classifications, and improving both human annotation agreement and machine‑learning prediction accuracy in production.

Evaluation Frameworkclassificationcommunity support

0 likes · 14 min read

T-LEAF: A Taxonomy Learning and Evaluation Framework for Airbnb Community Support Classification System

Alibaba Cloud Developer

Oct 10, 2018 · Artificial Intelligence

How Virtual Category Trees Boost E‑Commerce Search and Recommendation

This article explains how Alibaba builds a virtual category (CPV) system for Taobao by merging similar categories, splitting overly coarse ones, and constructing a hierarchical virtual category tree using methods such as PMI, title term similarity, frequent itemset mining, and graph‑embedding techniques, ultimately reducing user fatigue and improving CTR.

category mergingcategory splittinggraph embedding

0 likes · 16 min read