Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/5ICML 2026Poster· Reinforcement Learning / Multi-agent

Learning to Share: Selective Memory for Efficient Parallel Agentic Systems

Joseph Fioresi · Parth Parag Kulkarni · Ashmal Vayani · Song Wang · Mubarak Shah

智能体与工具强化学习与后训练效率与系统OpenReview

作者位次 #3/5ICML 2026Poster· Deep Learning / Large Language Models

SMILE: Extended Deep Submodular Function-Based Instruction and In-context Learning Demonstration Selection

Zihan Chen · Chengshuai Shi · Song Wang · Jundong Li · Cong Shen

理论与学习动力学OpenReview

作者位次 #4/7ICML 2026Poster· Deep Learning / Graph Neural Networks

Generalist Graph Anomaly Detection via Prototype-Based Distillation

Yiming Xu · Zihan Chen · Zhen Peng · Song Wang · Bin Shi · Bo Dong · Chao Shen

强化学习与后训练OpenReview

作者位次 #2/7ICML 2026Poster· Deep Learning / Large Language Models

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

Jianing Deng · Song Wang · Dongwei Wang · Zijie Liu · Tianlong Chen · Huanrui Yang · Jingtong Hu

效率与系统OpenReview

作者位次 #3/11ACL 2026Findings· Findings of ACL

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

Xu Shen · Qi Zhang · Song Wang · Zhen Tan · Xinyu Zhao · Laura Yao · Vaishnav Tadiparthi · Hossein Nourkhiz Mahjoub · Ehsan Moradi Pari · Kwonjoon Lee · Tianlong Chen

摘要

Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC, a metacognitive framework that endows MAS with real-time...

智能体与工具评测与基准长上下文与架构OpenReview 项目页

作者位次 #3/7KDD 2026Oral· Knowledge Discovery & Data Mining

How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge

Junhong Lin · Bing Zhang · Song Wang · Ziyan Liu · Dan Gutfreund · Julian Shun · Yada Zhu

检索与知识推理效率与系统OpenReview

Song Wang

获取完整研究档案

联系方式