6 papers
Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce
Shicheng Fan, Mingdai Yang, Duohao Wang +9
In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in…
Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents
Mingdai Yang, Shicheng Fan, Kejing Yu +5
LLM agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instru…
Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering
Shicheng Fan, Haochang Hao, Dehai Min +10
Process supervision during reinforcement learning (RL) post-training matters in factual question answering (QA) because responses receiving positive response-level rewards can stil…
CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
Hanrong Zhang, Shicheng Fan, Henry Peng Zou +11
Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained func…
Multi-Modal One-Shot Federated Ensemble Learning for Medical Data with Vision Large Language Model
Naibo Wang, Yuchen Deng, Shichen Fan +2
Federated learning (FL) has attracted considerable interest in the medical domain due to its capacity to facilitate collaborative model training while maintaining data privacy. How…
One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity
Naibo Wang, Yuchen Deng, Wenjie Feng +3
Traditional federated learning mainly focuses on parallel settings (PFL), which can suffer significant communication and computation costs. In contrast, one-shot and sequential fed…