1
2
DREAM: LLM-based Dynamic Role-playing via Event-Aware Memory Graph
用事件感知记忆图驱动LLM角色扮演，让AI角色动态记住经历，交互更真实。
arXiv:2608.05170v1 Announce Type: cross Abstract: Role-playing agents (RPAs) have emerged as a key application of large language models, enabling imme…
3
Sharpness-aware Model Merging with Salience Recovery for LLM-based Cross-Domain Sequential Recommendation
KDD'26前沿论文：锐度感知模型合并结合显著性恢复，突破LLM跨域顺序推荐性能瓶颈。
arXiv:2607.25366v1 Announce Type: cross Abstract: LLM-based Cross-Domain Sequential Recommendation (CDSR) leverages LLMs to enhance target performance…
4
StageGuard: Physiologically Constrained Sleep Staging
KDD 2026 论文：用生理约束提升睡眠分期准确率，打破纯数据驱动局限。
arXiv:2607.23284v1 Announce Type: new Abstract: Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpo…
5
Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?
Claude和Codex交叉审查代码，哪种配对更高效？KDD'26研究揭示答案。
arXiv:2607.21656v1 Announce Type: cross Abstract: Developers increasingly use two coding agents together: one writes a draft, and the other reviews it…
6
Semi-Supervised Text-Attributed Graph Distillation
图半监督蒸馏新方法被KDD2026录用，利用文本属性提升图表示学习效率。
arXiv:2607.20477v1 Announce Type: new Abstract: {\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph top…
7
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
向量化Trie结构加速LLM约束解码，专为生成式检索设计，在GPU等加速器上实现高效推理。
arXiv:2602.22647v2 Announce Type: replace-cross Abstract: Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. Howeve…
8
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
用LLM智能体模拟和审计联盟形成过程，打开多智能体协作研究新视角。
arXiv:2607.15095v1 Announce Type: new Abstract: The formation of political coalitions is a complex negotiation driven by both concrete policy objectiv…
9
Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
流式系统里，如何用不确定性感知决策规则，智能触发LLM调用而避免过量消耗，融合轻量模型实现高效推理。
arXiv:2607.13048v1 Announce Type: cross Abstract: Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (…
10
Aleena: Alignment Agent for Research Software Engineering Collaborations
专为研究软件工程协作设计的AI对齐代理Aleena，让AI队友更懂人类科学家的需求与节奏！
arXiv:2607.08043v1 Announce Type: cross Abstract: Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A …
11
日本 KDDI：信息泄露事件涉及超 1200 万电子邮件地址、超 700 万密码
日本电信巨头KDDI遭遇大规模数据泄露，超1200万邮箱和700万密码遭黑客窃取，影响持续一个月
IT之家 7 月 7 日消息，日本电信运营商 KDDI 今日表示，今年 5~6 月发生的其面向 ISP （IT之家注：互联网服务提供商） 运营商的电子邮件平台遭遇未经授权访问致使数据泄露事件 影响了超 1233 万用户的电子邮件地址和近 762 万用户的密码 。 IT之家了解到，KDDI 为一些日本…
12
Multi-Objective Exploration and Preference Optimization via Mutual Information
用互信息架起多目标探索与偏好优化的桥梁，ECML/PKDD 2026 最新研究，值得深度研读。
arXiv:2607.01392v1 Announce Type: new Abstract: Aligning large language models with diverse and heterogeneous human values requires multi-objective al…
13
Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
知识编辑与微调能否和平共处？这项研究揭示了两者相互干扰的脆弱平衡，为AI模型更新提供关键警示。
arXiv:2511.05852v4 Announce Type: replace Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language …
14
Little Brains, Big Feats: Exploring Compact Language Models
紧凑模型也能有大本事，看小参数如何撬动大语言模型性能，数据科学顶会研究值得一读。
arXiv:2606.30062v1 Announce Type: new Abstract: While large language models have been dominating the research landscape recently, small language model…
15
AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing
利用LLM实现电商定价中长期价值对齐，KDD 2026 oral论文，AI赋能商业决策新范式。
arXiv:2606.26787v1 Announce Type: cross Abstract: Traditional dynamic pricing models in large-scale e-commerce suffer from limited interpretability, p…
16
ECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction
利用心电图生成心脏磁共振影像做预训练，巧妙融合跨模态生成与疾病分类，KDD 2026 值得一读
arXiv:2601.20904v3 Announce Type: replace-cross Abstract: Cardiac Magnetic Resonance (CMR) imaging provides a comprehensive assessment of cardiac stru…
17
ARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery
突破生成模型因果盲区，ARIA以因果感知框架重塑材料发现中的大模型推理，KDD 2026前沿成果。
arXiv:2606.22375v1 Announce Type: new Abstract: Generative models have revolutionized the process of materials discovery, yet they often fail to satis…
18
EmoFSM: A Finite State Machine for Emotional Support Conversation
用有限状态机为情感支持对话构建结构化流程，提升对话连贯性与共情能力。
arXiv:2504.11837v3 Announce Type: replace-cross Abstract: Emotional support conversation (ESC) aims to alleviate people's emotional distress through e…
19
LLM-as-Code Agentic Programming for Agent Harness
提出 LLM-as-Code 智能体编程范式，为 Agent 框架提供全新开发思路，KDD 2026 最新研究。
arXiv:2606.15874v1 Announce Type: new Abstract: Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do n…
20
Generalizing GNNs with Tokenized Mixture of Experts
KDD 2026论文提出Tokenized MoE框架，用专家混合机制突破GNN泛化瓶颈
arXiv:2602.09258v2 Announce Type: replace Abstract: Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize…