3 citations · 6 across the 14 of their papers we have counts for
14 papers
Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI
Jiaqi Shao, Hanck Chen, Wei Zhang +2
Agent benchmarks increasingly evaluate repository editing, web research, terminal use, and long-horizon interaction. Their scores support capability claims only when the evaluation…
Do More Agents Help? Evaluating Accuracy and Cost in LLM Multi-Agent Workflows
Yuhang Fu, Ruishan Fang, Jiaqi Shao +5
Choosing whether to replace a single-agent controller requires evidence on both task performance and inference expenditure. We present BenchAgent, a shared evaluation framework, an…
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
Jiaqi Shao, Yiyi Lu, Yunzhen Zhang +1
Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant sessions (sessions not anno…
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
Suning Huang, Jiaqi Shao, Ke Wang +5
Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limit…
FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents
Jiaqi Shao, Yufeng Miao, Wei Zhang +1
Long-horizon reinforcement learning (RL) for large language models faces critical scalability challenges from unbounded context growth, leading to context folding methods that comp…
Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents
Jiaqi Shao, Yuxiang Lin, Munish Prasad Lohani +2
Recent work has explored training Large Language Model (LLM) search agents with reinforcement learning (RL) for open-domain question answering (QA). However, most evaluations focus…
Ten Challenging Problems in Federated Foundation Models
Tao Fan, Hanlin Gu, Xuemei Cao +30
Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of fed…
MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration
Siyuan Lu, Jiaqi Shao, Bing Luo +1
Large Language Model (LLM) based multi-agent systems (MAS) have shown promise in tackling complex tasks, but often rely on predefined roles and centralized coordination, limiting t…
Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentives
Jiaqi Shao, Tao Lin, Xiaojin Zhang +2
Federated Unlearning (FU) enables the removal of specific clients' data influence from trained models. However, in non-IID settings, removing clients creates critical side effects:…
Demo: FedCampus: A Real-world Privacy-preserving Mobile Application for Smart Campus via Federated Learning & Analytics
Jiaxiang Geng, Beilong Tang, Boyan Zhang +2
In this demo, we introduce FedCampus, a privacy-preserving mobile application for smart \underline{campus} with \underline{fed}erated learning (FL) and federated analytics (FA). Fe…
Cognitive Insights and Stable Coalition Matching for Fostering Multi-Agent Cooperation
Jiaqi Shao, Tianjun Yuan, Tao Lin +1
Cognitive abilities, such as Theory of Mind (ToM), play a vital role in facilitating cooperation in human social interactions. However, our study reveals that agents with higher To…
FedKit: Enabling Cross-Platform Federated Learning for Android and iOS
Sichang He, Beilong Tang, Boyan Zhang +4
We present FedKit, a federated learning (FL) system tailored for cross-platform FL research on Android and iOS devices. FedKit pipelines cross-platform FL development by enabling m…
Federated Unlearning: a Perspective of Stability and Fairness
Jiaqi Shao, Tao Lin, Xuanyu Cao +1
This paper explores the multifaceted consequences of federated unlearning (FU) with data heterogeneity. We introduce key metrics for FU assessment, concentrating on verification, g…
Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data
Jiaqi Shao, Shanshan Han, Chaoyang He +1
Federated heavy-hitter analytics involves the identification of the most frequent items within distributed data. Existing methods for this task often encounter challenges such as c…